Triple
T6000343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1914 Boston Braves |
E133578
|
entity |
| Predicate | notablePlayer |
P304
|
FINISHED |
| Object |
Joe Connolly
Joe Connolly was a Major League Baseball outfielder best known for his role on the 1914 "Miracle" Boston Braves championship team.
|
E575504
|
NE FINISHED |
How this triple was built (4 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: Joe Connolly | Statement: [1914 Boston Braves, notablePlayer, Joe Connolly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Connolly Context triple: [1914 Boston Braves, notablePlayer, Joe Connolly]
-
A.
Robert Connolly
Robert Connolly is an Australian filmmaker known for his work as a producer, director, and screenwriter on acclaimed feature films and television projects.
-
B.
Kevin Corrigan
Kevin Corrigan is an American character actor known for his offbeat, often darkly comic supporting roles in numerous independent films and major studio movies.
-
C.
Chris Donlon
Chris Donlon is a film editor known for his work on the feature film "Kicks."
-
D.
Tom Doherty
Tom Doherty is an American publisher best known as the founder of the science fiction and fantasy imprint Tor Books.
-
E.
Kevin Connor
Kevin Connor is a film editor known for his work on the satirical World War I musical film "Oh! What a Lovely War."
- 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: Joe Connolly Triple: [1914 Boston Braves, notablePlayer, Joe Connolly]
Generated description
Joe Connolly was a Major League Baseball outfielder best known for his role on the 1914 "Miracle" Boston Braves championship team.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Joe Connolly Target entity description: Joe Connolly was a Major League Baseball outfielder best known for his role on the 1914 "Miracle" Boston Braves championship team.
-
A.
Robert Connolly
Robert Connolly is an Australian filmmaker known for his work as a producer, director, and screenwriter on acclaimed feature films and television projects.
-
B.
Kevin Corrigan
Kevin Corrigan is an American character actor known for his offbeat, often darkly comic supporting roles in numerous independent films and major studio movies.
-
C.
Chris Donlon
Chris Donlon is a film editor known for his work on the feature film "Kicks."
-
D.
Tom Doherty
Tom Doherty is an American publisher best known as the founder of the science fiction and fantasy imprint Tor Books.
-
E.
Kevin Connor
Kevin Connor is a film editor known for his work on the satirical World War I musical film "Oh! What a Lovely War."
- F. None of above. chosen
Provenance (5 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_69c00872444c8190bfaf1739dcec765c |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04ee5e7bc8190aaa87605fa7b102e |
completed | March 22, 2026, 8:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c16e985f34819091d28debdd5a2950 |
completed | March 23, 2026, 4:47 p.m. |
| NEDg | Description generation | batch_69c1c27875348190a9239c1bfff02c5b |
completed | March 23, 2026, 10:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c1c67eeb908190abaa591db960ae9d |
completed | March 23, 2026, 11:02 p.m. |
Created at: March 22, 2026, 4:05 p.m.