Triple
T24380035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banu Abs |
E614581
|
entity |
| Predicate | hasNotableWarrior |
P63978
|
FINISHED |
| Object | Antarah ibn Shaddad |
—
|
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: Antarah ibn Shaddad | Statement: [Banu Abs, hasNotableWarrior, Antarah ibn Shaddad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableWarrior Context triple: [Banu Abs, hasNotableWarrior, Antarah ibn Shaddad]
-
A.
hasNotableHero
chosen
Indicates that an entity is associated with a particularly distinguished or prominent hero.
-
B.
isWarHeroOf
Indicates that one entity is recognized as a war hero in relation to, or on behalf of, another entity (such as a country, group, or cause).
-
C.
hasNotableWeaponNamedAfter
Indicates that an entity possesses a notable weapon that is named after another specific entity.
-
D.
notableCombatant
Indicates that an entity is recognized as a significant or distinguished participant in a particular conflict or combat event.
-
E.
hasNotableShogun
Indicates that an entity is associated with a historically notable shogun, such as by rule, leadership, or significant connection.
- 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_69e2d7e362e481909e32fe4ef8269d4f |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f293db31c481908484ab28921cd5fd |
completed | April 29, 2026, 11:27 p.m. |
| PD | Predicate disambiguation | batch_69f287c4a2b48190b80fb7a3c0e9b018 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:03 a.m.