Triple
T16599460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Graves |
E403293
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Bill Graves |
E403293
|
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: Bill Graves | Statement: [Bill Graves, name, Bill Graves]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bill Graves Context triple: [Bill Graves, name, Bill Graves]
-
A.
Bill Graves
chosen
Bill Graves is an American politician who served as the 43rd Governor of Kansas from 1995 to 2003.
-
B.
Herb Conaway
Herb Conaway is an American physician and Democratic politician who has long served in the New Jersey General Assembly.
-
C.
Bill Crawford
Bill Crawford is a former United States Air Force enlisted airman and janitor who was belatedly recognized with the Medal of Honor for his heroic actions during World War II.
-
D.
Don Payne
Don Payne was an American screenwriter and producer best known for his work on comedic television series like "The Simpsons" and superhero films such as "Thor."
-
E.
Harlan Crow
Harlan Crow is an American real estate investor, conservative political donor, and collector of historical artifacts, known for his leadership of Crow Holdings and his influence in Republican circles.
- 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_69d883880d0c81908b5fcd454e767b60 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35d74738c81909711654cf38af150 |
completed | April 18, 2026, 10:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0075a226788190bfad73ffb6b32ec4 |
completed | May 10, 2026, 12:10 p.m. |
Created at: April 10, 2026, 5:16 a.m.