Triple

T11349964
Position Surface form Disambiguated ID Type / Status
Subject Battle of the Col de Panissars E268814 entity
Predicate opposingForceStatus P19820 FINISHED
Object French army was retreating 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: French army was retreating | Statement: [Battle of the Col de Panissars, opposingForceStatus, French army was retreating]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: opposingForceStatus
Context triple: [Battle of the Col de Panissars, opposingForceStatus, French army was retreating]
  • A. opposingForcesStatus chosen
    Indicates the current state or condition of two or more forces that are in conflict or opposition to each other.
  • B. opposingForce
    Indicates a relationship where one entity actively resists, counters, or works against the actions, goals, or influence of another entity.
  • C. oppositionStatus
    Indicates that one entity’s stance, condition, or role is characterized by being against, resisting, or in conflict with another entity, proposal, or situation.
  • D. inForceStatus
    Indicates that a rule, agreement, or condition is currently active, valid, and legally or formally in effect.
  • E. hasOpposingForceType
    Indicates that one force is characterized as being of a type that opposes or counteracts another force.
  • 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_69d6aacbe18081909e5fadb50082dd96 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d80148e2048190a716b515d78efdd1 completed April 9, 2026, 7:43 p.m.
PD Predicate disambiguation batch_69d7e6f8aeb4819080476f16a69b2ee3 completed April 9, 2026, 5:50 p.m.
Created at: April 8, 2026, 9:33 p.m.