Triple
T21919799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Hunter |
E541274
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Dave Hunter |
—
|
NE NERFINISHED |
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: Dave Hunter | Statement: [Mark Hunter, sibling, Dave Hunter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dave Hunter Context triple: [Mark Hunter, sibling, Dave Hunter]
-
A.
Dave Hunter
chosen
Dave Hunter is a Canadian former professional ice hockey player who played as a left winger in the NHL, notably for the Edmonton Oilers during their 1980s dynasty.
-
B.
Simon Hunter
Simon Hunter is a British film director known for his work on genre films and character-driven dramas.
-
C.
Simon Hunter
Simon Hunter is a writer known in connection with the character Edie.
-
D.
Tony Hirst
Tony Hirst is a British voice actor and narrator best known for his work on television documentaries and factual series.
-
E.
Anthony Rogers
Anthony Rogers is the original name of the science fiction hero later known as Buck Rogers, a World War I veteran who awakens in a technologically advanced future.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c47c4b9c8190a5586a75f5f36453 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12339d88881909e726c9b081bd177 |
completed | April 28, 2026, 9:14 p.m. |
Created at: April 16, 2026, 7:44 p.m.