Triple
T19939174
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | One Eight Seven |
E479257
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Kevin Reynolds |
—
|
NE NERFINISHED |
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: Kevin Reynolds | Statement: [One Eight Seven, director, Kevin Reynolds]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kevin Reynolds Context triple: [One Eight Seven, director, Kevin Reynolds]
-
A.
Kevin Reynolds
chosen
Kevin Reynolds is an American film director best known for helming movies such as "Robin Hood: Prince of Thieves" and "Waterworld."
-
B.
Paul Darrow
Paul Darrow was the son of famed American lawyer Clarence Darrow and a businessman who managed many of his father's financial affairs.
-
C.
Brian J. Reynolds
Brian J. Reynolds is a cinematographer best known for his work on the crime film "Gang Related."
-
D.
Jeff Cronenweth
Jeff Cronenweth is an American cinematographer known for his stylish, atmospheric work on films such as "The Social Network" and collaborations with director David Fincher.
-
E.
Mike Hurley
Mike Hurley is a Canadian politician and former firefighter who serves as the mayor of Burnaby, British Columbia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e522a17c819095165d4d24939fd8 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65a19d77c819088bce99c94568d0d |
completed | April 20, 2026, 4:53 p.m. |
Created at: April 10, 2026, 1:53 p.m.