Triple

T11343209
Position Surface form Disambiguated ID Type / Status
Subject Afghan tribal forces E268650 entity
Predicate alliancePattern P8409 FINISHED
Object formed temporary alliances with Afghan rulers 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: formed temporary alliances with Afghan rulers | Statement: [Afghan tribal forces, alliancePattern, formed temporary alliances with Afghan rulers]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: alliancePattern
Context triple: [Afghan tribal forces, alliancePattern, formed temporary alliances with Afghan rulers]
  • A. newAlliancePattern
    Indicates the formation of a new cooperative or strategic alliance pattern between entities.
  • B. previousAlliancePattern chosen
    Indicates a recurring or characteristic way in which alliances were formed, structured, or aligned between entities in the past.
  • C. allianceType
    Indicates the specific kind or category of alliance relationship that exists between entities.
  • D. allianceStructure
    Indicates the organizational or relational configuration that defines how members of an alliance are structured and interconnected.
  • E. allianceUse
    Indicates that one party makes use of, benefits from, or leverages an alliance or allied relationship with another party.
  • 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_69d6aacb1f0881908c84a349fd1be047 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.