Triple
T9086320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sally Field |
E217763
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Peter Craig |
E420157
|
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: Peter Craig | Statement: [Sally Field, child, Peter Craig]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Craig Context triple: [Sally Field, child, Peter Craig]
-
A.
Peter Craig
chosen
Peter Craig is an American screenwriter and novelist known for co-writing major films such as "The Town," "The Batman," and "Top Gun: Maverick."
-
B.
Steven Craig
Steven Craig is best known as the former husband of acclaimed American actress Sally Field.
-
C.
Sam Craig
Sam Craig is a central character in the classic film "Woman of the Year," serving as the down-to-earth sports reporter whose relationship with high-profile journalist Tess Harding drives the movie’s romantic and thematic conflicts.
-
D.
Stephen Lyle Craig
Stephen Lyle Craig is an American former basketball player and businessman best known for twice marrying entertainer Marie Osmond.
-
E.
Ian Crafford
Ian Crafford is a film editor best known for his work on the James Bond movie "Never Say Never Again."
- 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_69ca83d7a0388190ba1af89ed7ba36f9 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc9654cb3c819089fa8c0ab0841c81 |
completed | April 1, 2026, 3:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d017c893fc819087d18db2383b9bb4 |
completed | April 3, 2026, 7:40 p.m. |
Created at: March 30, 2026, 7:13 p.m.