Triple

T17024915
Position Surface form Disambiguated ID Type / Status
Subject Chan Constance E413038 entity
Predicate name P16 FINISHED
Object Chan Constance E413038 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: Chan Constance | Statement: [Chan Constance, name, Chan Constance]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chan Constance
Context triple: [Chan Constance, name, Chan Constance]
  • A. Chan Constance chosen
    Chan Constance is the daughter of Hong Kong singer and actor Eason Chan.
  • B. Mary Ratcliffe
    Mary Ratcliffe is a relatively obscure individual known primarily through genealogical and historical records rather than for widely recognized public achievements.
  • C. Martha Marling
    Martha Marling is known as the sister of English folk singer-songwriter Laura Marling.
  • D. Elizabeth Stirling
    Elizabeth Stirling was the mother of lexicographer James Murray, who became the primary editor of the Oxford English Dictionary.
  • E. Constance
    Constance is a historic city on Lake Constance in present-day Germany, best known as the site of the early 15th-century Council of Constance that ended the Western Schism in the Catholic Church.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d5d371148190a60d32a72abec09a completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b53306081908972a0a5db474b6c completed May 10, 2026, 11:57 p.m.
Created at: April 10, 2026, 5:33 a.m.