Triple
T7055491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Holden |
E164077
|
entity |
| Predicate | castMemberWith |
P74774
|
FINISHED |
| Object | William Tracy |
E158927
|
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: William Tracy | Statement: [Mary Holden, castMemberWith, William Tracy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Tracy Context triple: [Mary Holden, castMemberWith, William Tracy]
-
A.
William Tracy
chosen
William Tracy was an American film actor best known for his comedic roles in 1930s and 1940s Hollywood movies.
-
B.
William Tharp
William Tharp was a 19th-century American politician who served as the 36th Governor of Delaware.
-
C.
Walter L. Huber
Walter L. Huber was a prominent American civil engineer and researcher recognized for his significant contributions to the field, commemorated by the ASCE’s Walter L. Huber Civil Engineering Research Prize.
-
D.
George Wheeler
George Wheeler was a 19th-century American surveyor and army officer best known for leading the Wheeler Survey, a major U.S. government exploration and mapping expedition of the American West.
-
E.
William McDermott
William McDermott is a personal name shared by multiple individuals, including various professionals and public figures, rather than referring to a single widely recognized person.
- 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_69c68861678881909961ddf4d779f750 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e77415e88190ab65137382f1b155 |
completed | March 27, 2026, 8:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7a316374c81908deeb60b8f58a3c8 |
completed | March 28, 2026, 9:44 a.m. |
Created at: March 27, 2026, 2:38 p.m.