Triple
T19547192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | So Big (1953 film) |
E489103
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Richard Beymer |
—
|
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 Beymer | Statement: [So Big (1953 film), starring, Richard Beymer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Beymer Context triple: [So Big (1953 film), starring, Richard Beymer]
-
A.
Richard Beymer
chosen
Richard Beymer is an American actor best known for playing Tony in the 1961 film adaptation of the musical "West Side Story."
-
B.
Julian Kaye
Julian Kaye is a charismatic Los Angeles male escort whose luxurious lifestyle unravels when he becomes entangled in a murder investigation.
-
C.
Eric Portman
Eric Portman was a British stage and film actor known for his intense character roles in mid-20th-century cinema, particularly in wartime and thriller films.
-
D.
Ormond Beatty
Ormond Beatty was a 19th-century American educator and academic administrator best known for serving as president of Centre College in Kentucky.
-
E.
Billy Hartnett
Billy Hartnett is the commonly used name for William Hartnett, likely referring to him in informal or public contexts.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63d2d8a6081908e9bb3a6f5d85896 |
completed | April 20, 2026, 2:50 p.m. |
Created at: April 10, 2026, 1:41 p.m.