Triple

T9604538
Position Surface form Disambiguated ID Type / Status
Subject Battle of Immae E231935 entity
Predicate opponent P437 FINISHED
Object Zabdas E801503 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: Zabdas | Statement: [Battle of Immae, opponent, Zabdas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zabdas
Context triple: [Battle of Immae, opponent, Zabdas]
  • A. Zabdas chosen
    Zabdas was a prominent 3rd-century Palmyrene general who led Queen Zenobia’s forces in major campaigns against the Roman Empire.
  • B. Zababa
    Zababa is an ancient Mesopotamian war god particularly venerated in the city of Kish.
  • C. Zardoz
    Zardoz is a 1974 science fiction film directed by John Boorman, known for its surreal, dystopian vision and starring Sean Connery in one of his most unconventional roles.
  • D. Azdak
    Azdak is a shrewd, unorthodox village judge whose rough-edged wisdom and sense of justice drive the central conflict in Bertolt Brecht’s play "The Caucasian Chalk Circle."
  • E. Zorzor
    Zorzor is a town in northwestern Liberia that serves as one of the main urban centers of Lofa County.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca8484838c8190b2049199d22fef70 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9a5e4a7c8190830b5ad9762ece46 completed April 1, 2026, 10:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1821dd3a88190bbba0a2f24c437e2 completed April 4, 2026, 9:26 p.m.
Created at: March 30, 2026, 8:08 p.m.