Triple
T33505021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ward–Gatti II |
E858087
|
entity |
| Predicate | featuresFighter |
P101800
|
FINISHED |
| Object | Micky Ward |
E244200
|
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: Micky Ward | Statement: [Ward–Gatti II, featuresFighter, Micky Ward]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresFighter Context triple: [Ward–Gatti II, featuresFighter, Micky Ward]
-
A.
featuredFighter
chosen
Indicates that a particular fighter is highlighted or prominently showcased in a given context or event.
-
B.
hasFighter
Indicates that an entity possesses, controls, or is associated with a fighter (such as a combatant, combat vehicle, or fighting unit).
-
C.
featuresCharacterWith
Indicates that one entity (such as a work or product) includes or presents a particular character as part of its content.
-
D.
primaryFighterModel
Indicates that one entity is the main or standard fighter aircraft model associated with another entity (such as a country, air force, or military unit).
-
E.
fightingAttribute
Indicates a relationship where one entity’s characteristics or properties are associated with combat or fighting-related capabilities of another entity.
- F. None of above.
Provenance (4 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_69f3497660508190a541826a81f7e9ab |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a01b841f5508190832bba00cf795bad |
completed | May 11, 2026, 11:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3689b30af88190a8b18eb2a9117c5b |
completed | June 20, 2026, 12:38 p.m. |
| PD | Predicate disambiguation | batch_6a01b59541fc8190a9b13a55327c4aa1 |
completed | May 11, 2026, 10:55 a.m. |
Created at: May 1, 2026, 1:38 a.m.