Triple
T12877367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cocktail |
E308002
|
entity |
| Predicate | basedOnWorkAuthor |
P2806
|
FINISHED |
| Object | Heywood Gould |
E260540
|
NE FINISHED |
How this triple was built (2 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: Heywood Gould | Statement: [Cocktail, basedOnWorkAuthor, Heywood Gould]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heywood Gould Context triple: [Cocktail, basedOnWorkAuthor, Heywood Gould]
-
A.
Heywood Gould
chosen
Heywood Gould is an American screenwriter, director, and novelist known for writing films such as "The Boys from Brazil" and "Fort Apache, The Bronx."
-
B.
James Gould
James Gould was an American jurist and legal educator known for his influential role in early 19th-century legal training in the United States.
-
C.
George Oatley
George Oatley was a British architect best known for designing prominent early 20th-century buildings in Bristol, England.
-
D.
James Isaacs
James Isaacs is a game designer best known for his work on the racing title Mad Dash Racing.
-
E.
George Selwyn
George Selwyn was an 18th-century English politician and noted wit, famed for his macabre sense of humor and prominent role in London high society.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d7bdf69bc48190af6c2621f28ca351 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d970fa8474819086a8af3c90f3ca84 |
completed | April 10, 2026, 9:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f716b63ad481909eb461d923f0d0c2 |
completed | May 3, 2026, 9:34 a.m. |
Created at: April 9, 2026, 5:38 p.m.