Triple
T8817980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sabine Willett |
E209828
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Willett |
E209828
|
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: Willett | Statement: [Sabine Willett, familyName, Willett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Willett Context triple: [Sabine Willett, familyName, Willett]
-
A.
Willett
chosen
Willett is a surname of English origin borne by various notable individuals, including American Revolutionary War officer and politician Marinus Willett.
-
B.
Montgomerie
Montgomerie is a variant spelling of the surname Montgomery, historically associated with Scottish nobility and clans.
-
C.
Willetts
Willetts is an English surname borne by various individuals, including figures in politics, academia, and sports.
-
D.
Hargreaves
Hargreaves is an English surname most notably associated with James Hargreaves, the 18th-century inventor of the spinning jenny.
-
E.
Irving Green
Irving Green was an American music executive best known as a co-founder and influential leader of Mercury Records, where he helped shape mid-20th-century popular music.
- 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_69ca8364e13081909c85fe80f44fe86f |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc600d267c81909e145e58af08e523 |
completed | April 1, 2026, midnight |
| NED1 | Entity disambiguation (via context triple) | batch_69cfab68ff308190b37b2202e7ccbab3 |
completed | April 3, 2026, 11:58 a.m. |
Created at: March 30, 2026, 6:46 p.m.