Triple

T4956342
Position Surface form Disambiguated ID Type / Status
Subject Laius E111289 entity
Predicate spouse P13 FINISHED
Object Epicasta E479325 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: Epicasta | Statement: [Laius, spouse, Epicasta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Epicasta
Context triple: [Laius, spouse, Epicasta]
  • A. Epicasta chosen
    Epicasta is a figure in Greek mythology known primarily as the mother of Antigone.
  • B. Euodia
    Euodia is a Christian woman mentioned in the New Testament book of Philippians, known for a disagreement with another woman named Syntyche that Paul urges them to resolve.
  • C. Phalanthos
    Phalanthos is a figure from Greek legend, often depicted as a Spartan or Parthenian leader associated with the mythic founding of the city of Tarentum in southern Italy.
  • D. Hesperis
    Hesperis is a figure from Greek mythology, often associated with the evening or the West and sometimes linked to the Hesperides, the nymphs of the evening and golden light.
  • E. Leucas
    Leucas was an ancient Greek city and island in the Ionian Sea, known for its strategic location and later prominence as Leucadia (modern Lefkada).
  • 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_69bd4418390c8190b7e9766a2512ce55 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd71d6ba9c8190932f8d81240c3f56 completed March 20, 2026, 4:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69be81de17748190a26abda7d3703b8e completed March 21, 2026, 11:32 a.m.
Created at: March 20, 2026, 1:32 p.m.