Triple

T5973726
Position Surface form Disambiguated ID Type / Status
Subject Narses E132934 entity
Predicate opponent P437 FINISHED
Object Teia E340638 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: Teia | Statement: [Narses, opponent, Teia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Teia
Context triple: [Narses, opponent, Teia]
  • A. Teia chosen
    Teia was the final king of the Ostrogoths in Italy, known for leading their last resistance against the Eastern Roman Empire in the mid-6th century.
  • B. Nebula
    Nebula is a cybernetically enhanced alien assassin and former daughter of Thanos who becomes a key member of the Guardians of the Galaxy in the Marvel Cinematic Universe.
  • C. Nebula
    Nebula is an independent, creator-owned streaming platform focused on educational and documentary-style content from popular online video creators.
  • D. Galaxia
    Galaxia is a fictional, galaxy-spanning group consciousness proposed in Isaac Asimov’s science fiction universe as an ultimate evolutionary step for intelligent life.
  • E. Antareen
    Antareen is a 1993 Indian Bengali-language film directed by Mrinal Sen, known for its introspective exploration of human isolation and relationships.
  • 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_69c0086deab081908550159ca23eec9b completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04a01dd4081909097342afff31f9b completed March 22, 2026, 7:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e41459c88190a9e0ee0321946e57 completed March 23, 2026, 6:56 a.m.
Created at: March 22, 2026, 4:03 p.m.