Triple
T22306172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elaine Vassal |
E551379
|
entity |
| Predicate | worksWith |
P398
|
FINISHED |
| Object | Richard Fish |
—
|
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: Richard Fish | Statement: [Elaine Vassal, worksWith, Richard Fish]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Fish Context triple: [Elaine Vassal, worksWith, Richard Fish]
-
A.
Richard Fish
chosen
Richard Fish is a quirky, money-driven yet oddly principled lawyer and partner at the Cage & Fish law firm on the television series "Ally McBeal."
-
B.
Donald Goines
Donald Goines was an American author known for his gritty, influential urban fiction novels depicting the harsh realities of inner-city life.
-
C.
Ed Kemper
Ed Kemper is an American serial killer and necrophile, known for murdering his grandparents, mother, and several young women in the 1960s and 1970s, and for later cooperating extensively with FBI profilers.
-
D.
Jeffrey Dahmer
Jeffrey Dahmer was an American serial killer and sex offender notorious for murdering and dismembering 17 young men and boys between 1978 and 1991.
-
E.
Fred E. West
Fred E. West was an American cinematographer known for his work on mid-20th-century genre and B-movies, including science fiction and horror films.
- 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_69e11e46c0188190800181a4233f28fe |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f157276d3c8190a55c93760a986cdc |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:41 p.m.