Triple

T17281266
Position Surface form Disambiguated ID Type / Status
Subject Maud Marshal E419533 entity
Predicate sibling P363 FINISHED
Object Joan Marshal E411330 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: Joan Marshal | Statement: [Maud Marshal, sibling, Joan Marshal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joan Marshal
Context triple: [Maud Marshal, sibling, Joan Marshal]
  • A. Joan Marshal chosen
    Joan Marshal was a 13th-century Anglo-Norman noblewoman, one of the daughters of the famed knight and statesman William Marshal, 1st Earl of Pembroke.
  • B. Joan Boniface Winnifrith
    Joan Boniface Winnifrith was the English actress better known by her stage name Anna Lee, who appeared in numerous British and American films and television series.
  • C. Joan
    Joan is a feminine given name of Hebrew origin, commonly used in English-speaking countries.
  • D. Joan
    Joan is the birth name of Joni Mitchell, the influential Canadian singer-songwriter and painter renowned for her poetic lyrics and innovative compositions.
  • E. Joan
    Joan is a central character in the 1986 romantic comedy-drama film "About Last Night," which explores the complexities of modern relationships.
  • 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_69d886da626481908a14ce7830329a35 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e4332a4c008190b44f4145d0e94a21 completed April 19, 2026, 1:43 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0180d29f4881908694f0182930d716 completed May 11, 2026, 7:10 a.m.
Created at: April 10, 2026, 5:40 a.m.