Triple

T19831981
Position Surface form Disambiguated ID Type / Status
Subject Creon E476483 entity
Predicate notableWork P4 FINISHED
Object Antigone NE NERFINISHED

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: Antigone | Statement: [Creon, notableWork, Antigone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Antigone
Context triple: [Creon, notableWork, Antigone]
  • A. Antigone chosen
    Antigone is a tragic heroine from Greek mythology and Sophocles’ Theban plays, known for defying royal authority to honor her family and the gods.
  • B. Antigone
    Antigone is a small village located in Gjirokastër County in southern Albania, known for its proximity to the archaeological site of ancient Antigonea.
  • C. Antigone
    Antigone is a genus of large, long-legged and long-necked cranes that includes species such as the sarus crane and sandhill crane.
  • D. Nerde Antigone
    Nerde Antigone is a notable poetic work by the prominent Turkish modernist poet Edip Cansever.
  • E. L’Egisto
    L’Egisto is a 17th-century Italian opera by Francesco Cavalli, known for its expressive early Baroque style and mythological subject matter.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e51c7c188190b926f3a2a7b5f881 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e656ce68b48190aa25b29d0b6ea021 completed April 20, 2026, 4:39 p.m.
Created at: April 10, 2026, 1:50 p.m.