Triple
T15347666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MetLife |
E366965
|
entity |
| Predicate | hasFounder |
P104
|
FINISHED |
| Object | William P. Stewart |
E366965
|
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 P. Stewart | Statement: [MetLife, hasFounder, William P. Stewart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William P. Stewart Context triple: [MetLife, hasFounder, William P. Stewart]
-
A.
William P. Stewart
chosen
William P. Stewart was an American businessman best known as a founder of the major insurance company MetLife.
-
B.
Lewis J. Boies
Lewis J. Boies was the third husband of Hollywood actress and inventor Hedy Lamarr.
-
C.
Leonard Q. Ross
Leonard Q. Ross was the pen name of humorist and writer Leo Rosten, known for his witty stories and contributions to American literature and film.
-
D.
James Robertson Justice
James Robertson Justice was a British character actor known for his booming voice and authoritative screen presence in mid-20th-century films.
-
E.
James R. Wilson
James R. Wilson is a notable alumnus of Ohio Northern University recognized for his professional achievements following his education there.
- 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_69d85a1355608190a6673ddb67231d54 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e1749bc8190a8b9cbcb27288a5b |
completed | April 16, 2026, 1:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2cec4f2481908fae5209bfd48dcf |
completed | May 9, 2026, 12:47 p.m. |
Created at: April 10, 2026, 3:17 a.m.