Triple
T23034546
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feherty |
E573556
|
entity |
| Predicate | hasNotableGuest |
P10756
|
FINISHED |
| Object | John Daly |
—
|
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: John Daly | Statement: [Feherty, hasNotableGuest, John Daly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Daly Context triple: [Feherty, hasNotableGuest, John Daly]
-
A.
John Daly
John Daly was a local landowner and civic figure after whom the Californian city of Daly City was named.
-
B.
John Daly
John Daly was a prominent British film producer known for backing influential independent and Oscar-winning films through his company Hemdale Film Corporation.
-
C.
John Daly
John Daly is a cinematographer known for his work on the 1995 film adaptation of Jane Austen's "Persuasion."
-
D.
John Daly
chosen
John Daly is an American professional golfer known for his long drives, unorthodox lifestyle, and two major championship victories.
-
E.
John Charles Daly
John Charles Daly was an American radio and television newsman and game show host best known for moderating the long-running panel show "What's My Line?".
- 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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18483e5848190977b1bdb1b83d187 |
completed | April 29, 2026, 4:09 a.m. |
Created at: April 17, 2026, 3:53 p.m.