Triple
T2385791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Hart |
E48818
|
entity |
| Predicate | fightingStyle |
P35675
|
FINISHED |
| Object | hand-to-hand combat |
—
|
LITERAL 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: hand-to-hand combat | Statement: [Harry Hart, fightingStyle, hand-to-hand combat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fightingStyle Context triple: [Harry Hart, fightingStyle, hand-to-hand combat]
-
A.
martialArt
Indicates that one entity practices, performs, or is associated with a specific martial art style or discipline in relation to another entity.
-
B.
methodOfCombat
chosen
Indicates the specific technique, style, or means by which an entity engages in combat or fighting.
-
C.
isGrapplingArt
Indicates that the subject is a martial art or combat style primarily focused on grappling techniques such as holds, locks, and throws.
-
D.
hasFightingStance
Indicates that an entity adopts or is characterized by a particular combat or fighting posture.
-
E.
fightingOutOf
Indicates that an individual is competing or representing themselves in a fight or match while being officially associated with a particular location, camp, or organization.
- F. None of above.
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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc7d8a918819089a210e74e13be6e |
completed | March 7, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69abc59f73f08190924a36d7d475d8f4 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:57 p.m.