Triple
T5019954
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anne Durant |
E112826
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Durant |
E50984
|
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: Durant | Statement: [Anne Durant, familyName, Durant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Durant Context triple: [Anne Durant, familyName, Durant]
-
A.
Durant
chosen
Durant is a surname most famously associated with William C. Durant, the pioneering American automobile magnate who co-founded General Motors.
-
B.
Kevin Durant
Kevin Durant is an American professional basketball star widely regarded as one of the greatest scorers in NBA history, with multiple championships and MVP awards.
-
C.
Rio Durant
Rio Durant is a multi-armed Ardennian pilot and criminal operative in the Star Wars universe, best known for serving on Tobias Beckett’s crew in Solo: A Star Wars Story.
-
D.
Ken Durant
Ken Durant is an individual notable enough to be recognized as a namesake of the surname Durant.
-
E.
Russell Westbrook
Russell Westbrook is an American professional basketball point guard known for his explosive athleticism, relentless playing style, and multiple NBA triple-double and MVP accolades.
- 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_69bd4435c2f48190be593158cbfcf8a3 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7342c62881909acb35849da8761c |
completed | March 20, 2026, 4:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be9c5e06fc8190bdd875c04cefd789 |
completed | March 21, 2026, 1:25 p.m. |
Created at: March 20, 2026, 1:36 p.m.