Triple
T7914564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holly Hunter |
E183786
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Hunter |
E238950
|
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: Hunter | Statement: [Holly Hunter, familyName, Hunter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hunter Context triple: [Holly Hunter, familyName, Hunter]
-
A.
Hunter
Hunter is an Australian federal electoral division in New South Wales, historically centered on coal mining regions and represented in the House of Representatives.
-
B.
Hunter
chosen
Hunter is a common English surname of occupational origin, historically referring to someone who hunted game for a living.
-
C.
Hunter
Hunter is a British heritage brand best known for its iconic rubber Wellington boots and outdoor footwear.
-
D.
Hunter
Hunter is a formidable and enigmatic bodyguard and warrior in Neil Gaiman's urban fantasy novel "Neverwhere," renowned for her unmatched prowess in tracking and combat within the hidden world of London Below.
-
E.
Die Hart
Die Hart is an action-comedy series starring Kevin Hart as a fictionalized version of himself trying to become an action movie star, blending Hollywood satire with over-the-top stunts.
- 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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a759b548190af2e2aa0705d7051 |
completed | March 31, 2026, 3:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5bdfb8d0819089cf1268df61bcdc |
completed | March 31, 2026, 5:30 a.m. |
Created at: March 30, 2026, 5:04 p.m.