Triple

T707403
Position Surface form Disambiguated ID Type / Status
Subject Mary E14130 entity
Predicate spouse P13 FINISHED
Object Joseph E8383 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: Joseph | Statement: [Mary, spouse, Joseph]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joseph
Context triple: [Mary, spouse, Joseph]
  • A. Joseph
    Joseph is the first name of J. C. R. Licklider, a pioneering computer scientist often regarded as a key figure in the development of the internet and interactive computing.
  • B. Joseph chosen
    Joseph is the husband of Mary in the New Testament and the earthly guardian of Jesus, venerated in Christianity as a model of humility, obedience, and fatherhood.
  • C. Joseph
    Joseph is the given name of the French mathematician and physicist Jean-Baptiste Joseph Fourier, known for developing Fourier analysis and Fourier series.
  • D. Joseph
    Joseph is the full given name of American sportscaster Joe Buck, known for his play-by-play announcing of major NFL and MLB games.
  • E. Joseph
    Joseph is the given name of Joe Fulks, an early professional basketball star often credited as one of the NBA’s first great scorers.
  • 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_69a493494ec48190ae6751683625a9ba completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a5477bb48190a2032edc83a24720 completed March 1, 2026, 8:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7927e57d48190a9e1f34c39501680 completed March 4, 2026, 2:01 a.m.
Created at: March 1, 2026, 7:36 p.m.