Triple
T3561648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1996 MLS Cup |
E75351
|
entity |
| Predicate | D.C. United captain |
P14876
|
FINISHED |
| Object |
John Harkes
John Harkes is a former American soccer midfielder who was a key figure for the U.S. national team and Major League Soccer in the 1990s.
|
E369071
|
NE FINISHED |
How this triple was built (5 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: John Harkes | Statement: [1996 MLS Cup, D.C. United captain, John Harkes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Harkes Context triple: [1996 MLS Cup, D.C. United captain, John Harkes]
-
A.
Jason Kreis
Jason Kreis is an American soccer coach and former player best known for leading Real Salt Lake to an MLS Cup title and later managing several Major League Soccer clubs.
-
B.
Dwight Yorke
Dwight Yorke is a retired Trinidad and Tobago striker best known for his prolific Premier League career, particularly with Aston Villa and Manchester United, with whom he won the treble in 1999.
-
C.
Landon Donovan
Landon Donovan is a retired American soccer player widely regarded as one of the greatest in U.S. history, known for his prolific MLS and U.S. national team careers and numerous championships.
-
D.
Clint Dempsey
Clint Dempsey is a retired American soccer forward and attacking midfielder, widely regarded as one of the greatest U.S. players of all time for his prolific club career in MLS and the Premier League and his record-tying goal tally with the U.S. national team.
-
E.
Tim Cahill
Tim Cahill is an Australian former professional footballer best known as a prolific attacking midfielder and iconic national-team star, particularly remembered for his goals at multiple FIFA World Cups.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: John Harkes Triple: [1996 MLS Cup, D.C. United captain, John Harkes]
Generated description
John Harkes is a former American soccer midfielder who was a key figure for the U.S. national team and Major League Soccer in the 1990s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Harkes Target entity description: John Harkes is a former American soccer midfielder who was a key figure for the U.S. national team and Major League Soccer in the 1990s.
-
A.
Jason Kreis
Jason Kreis is an American soccer coach and former player best known for leading Real Salt Lake to an MLS Cup title and later managing several Major League Soccer clubs.
-
B.
Dwight Yorke
Dwight Yorke is a retired Trinidad and Tobago striker best known for his prolific Premier League career, particularly with Aston Villa and Manchester United, with whom he won the treble in 1999.
-
C.
Landon Donovan
Landon Donovan is a retired American soccer player widely regarded as one of the greatest in U.S. history, known for his prolific MLS and U.S. national team careers and numerous championships.
-
D.
Clint Dempsey
Clint Dempsey is a retired American soccer forward and attacking midfielder, widely regarded as one of the greatest U.S. players of all time for his prolific club career in MLS and the Premier League and his record-tying goal tally with the U.S. national team.
-
E.
Tim Cahill
Tim Cahill is an Australian former professional footballer best known as a prolific attacking midfielder and iconic national-team star, particularly remembered for his goals at multiple FIFA World Cups.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: D.C. United captain Context triple: [1996 MLS Cup, D.C. United captain, John Harkes]
-
A.
awayTeamCaptain
Indicates that one entity serves as the captain or designated leader of the away (visiting) team in a competition or match.
-
B.
Michael Bradley
Indicates a relationship or action involving an entity named Michael Bradley, though the specific nature of the relationship or action is not defined by the predicate alone.
-
C.
teamCaptain
chosen
Indicates that one entity serves as the captain or designated leader of a particular team.
-
D.
homeTeamCaptain
Indicates that one entity serves as the captain of the home team in a given game or match in relation to the other entity.
-
E.
winningCaptain
Indicates that the subject is the captain of a team that has won a particular match, tournament, or competition.
- F. None of above.
Provenance (6 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ad85d45090819086f34fb85d850a1e |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc08bdde88190915d2f6ddf26e00e |
completed | March 8, 2026, 6:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3bba21960819094676de7c4740fd9 |
completed | March 13, 2026, 7:24 a.m. |
| NEDg | Description generation | batch_69b3bf69741481909e3d5ed71bb0e026 |
completed | March 13, 2026, 7:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b3f299cfd08190948e602e8efab213 |
completed | March 13, 2026, 11:18 a.m. |
| PD | Predicate disambiguation | batch_69adb834779081908468e182d5f6cf02 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:21 p.m.