Triple
T10738813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gazelle |
E253264
|
entity |
| Predicate | antagonistOf |
P18963
|
FINISHED |
| Object | Harry Hart |
E48818
|
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: Harry Hart | Statement: [Gazelle, antagonistOf, Harry Hart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Hart Context triple: [Gazelle, antagonistOf, Harry Hart]
-
A.
Harry Hart
chosen
Harry Hart is a suave, highly skilled British secret agent and mentor figure in the Kingsman film series.
-
B.
David Nobbs
David Nobbs was a British comedy writer and novelist best known for his sharp, character-driven humor and influential work in television sitcoms and comic fiction.
-
C.
Peter Kerrigan
Peter Kerrigan was a British actor known for his work in television and film, particularly in socially conscious dramas of the late 20th century.
-
D.
George Hackathorne
George Hackathorne was an American silent film actor active in the 1910s and 1920s, known for his roles in early Hollywood productions.
-
E.
Lee Chandler
Lee Chandler is the emotionally withdrawn Boston janitor and handyman at the center of the film "Manchester by the Sea," whose tragic past drives the movie’s exploration of grief and guilt.
- 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_69d6aa5e51e8819095f06881cecf152e |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d710424d8c81908ee9b59d622f2af5 |
completed | April 9, 2026, 2:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de22ed6edc8190beb76bd2971c7cec |
completed | April 14, 2026, 11:20 a.m. |
Created at: April 8, 2026, 9:14 p.m.