Triple

T11007980
Position Surface form Disambiguated ID Type / Status
Subject Candlemas E260169 entity
Predicate hasAssociatedFigure P2830 FINISHED
Object Prophetess Anna E260167 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: Prophetess Anna | Statement: [Candlemas, hasAssociatedFigure, Prophetess Anna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prophetess Anna
Context triple: [Candlemas, hasAssociatedFigure, Prophetess Anna]
  • A. prophetess Anna chosen
    Prophetess Anna is a biblical figure in the Gospel of Luke, an elderly widow and devout woman who recognized the infant Jesus as the Messiah when he was presented in the Temple.
  • B. Emmelia of Caesarea
    Emmelia of Caesarea was a 4th-century Christian noblewoman and saint, known as the matriarch of a prominent Cappadocian family that produced several influential Church Fathers and saints.
  • C. Tirza
    Tirza is a river in Latvia that serves as one of the tributaries feeding into the larger Gauja River system.
  • D. Aikaterine
    Aikaterine is an ancient Greek female given name that is the linguistic ancestor of various forms such as Katherine and Kathleen.
  • E. Sibyl
    Sibyl is a prophetic figure from ancient Greco-Roman tradition, typically depicted as a woman endowed with divine insight and the power of inspired oracles.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79757bdcc8190900b267826eece21 completed April 9, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3e717481c81908800cd785537c8fc completed April 18, 2026, 8:18 p.m.
Created at: April 8, 2026, 9:25 p.m.