Triple
T4512649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yadava |
E102085
|
entity |
| Predicate | hasRoleInEpic |
P161
|
FINISHED |
| Object | allies of Pandavas |
—
|
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: allies of Pandavas | Statement: [Yadava, hasRoleInEpic, allies of Pandavas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoleInEpic Context triple: [Yadava, hasRoleInEpic, allies of Pandavas]
-
A.
hasNotableRoleIn
Indicates that an entity holds a significant or noteworthy role or function within another entity, event, work, or context.
-
B.
hasRole
chosen
Indicates that an entity occupies, performs, or is assigned a specific role or function in relation to another entity or context.
-
C.
hasRuleExperimentationRole
Indicates that an entity holds a role or permission related to creating, managing, or testing rules in an experimentation or A/B testing context.
-
D.
appliedDuringRole
Indicates that an action, method, or process was carried out specifically while an entity was serving in a particular role or position.
-
E.
hasStageRole
Indicates that an entity performs or holds a specific role or character in a staged performance or theatrical production.
- 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_69bd43d6251c81909deecce3e6e9d69c |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5722d8fc81909c5f2d9a38d17a6b |
completed | March 20, 2026, 2:18 p.m. |
| PD | Predicate disambiguation | batch_69bd5218afb4819087c99e0a1f22e137 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:01 p.m.