Triple
T2308106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annie Hall |
E51888
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Tony Roberts
Tony Roberts is an American actor best known for his frequent collaborations with Woody Allen in films such as "Annie Hall."
|
E287287
|
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: Tony Roberts | Statement: [Annie Hall, starring, Tony Roberts]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tony Roberts Context triple: [Annie Hall, starring, Tony Roberts]
-
A.
Joe Roberts
Joe Roberts was an American silent film actor best known for his frequent collaborations with comedian Buster Keaton in the 1920s.
-
B.
Ed Morrison
Ed Morrison is an English rugby union referee best known for officiating major international matches, including the 1995 Rugby World Cup final.
-
C.
Jonathan Roberts
Jonathan Roberts is an American screenwriter best known for co-writing Disney’s animated classic "The Lion King."
-
D.
Fred Robinson
Fred Robinson was an American jazz trombonist active in the 1920s and 1930s, known for his work with Louis Armstrong and other leading early jazz ensembles.
-
E.
Don Graham
Don Graham is a real estate developer best known for his role in creating Honolulu’s Ala Moana Center, one of the largest open-air shopping malls in the world.
- 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: Tony Roberts Triple: [Annie Hall, starring, Tony Roberts]
Generated description
Tony Roberts is an American actor best known for his frequent collaborations with Woody Allen in films such as "Annie Hall."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tony Roberts Target entity description: Tony Roberts is an American actor best known for his frequent collaborations with Woody Allen in films such as "Annie Hall."
-
A.
Joe Roberts
Joe Roberts was an American silent film actor best known for his frequent collaborations with comedian Buster Keaton in the 1920s.
-
B.
Ed Morrison
Ed Morrison is an English rugby union referee best known for officiating major international matches, including the 1995 Rugby World Cup final.
-
C.
Jonathan Roberts
Jonathan Roberts is an American screenwriter best known for co-writing Disney’s animated classic "The Lion King."
-
D.
Fred Robinson
Fred Robinson was an American jazz trombonist active in the 1920s and 1930s, known for his work with Louis Armstrong and other leading early jazz ensembles.
-
E.
Don Graham
Don Graham is a real estate developer best known for his role in creating Honolulu’s Ala Moana Center, one of the largest open-air shopping malls in the world.
- 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_69a88b0bb30c81908ded03b006d29387 |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abc605cf808190a326e6c78e3f9166 |
completed | March 7, 2026, 6:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afa03e7b6c81909e61671bd4435723 |
completed | March 10, 2026, 4:38 a.m. |
| NEDg | Description generation | batch_69afa0c2241081909998659865534ab2 |
completed | March 10, 2026, 4:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69afa1a7d9b48190a8b14a7d209e1f26 |
completed | March 10, 2026, 4:44 a.m. |
Created at: March 4, 2026, 7:49 p.m.