Triple

T6595491
Position Surface form Disambiguated ID Type / Status
Subject Morris Swadesh E148463 entity
Predicate spouse P13 FINISHED
Object Mary Haas E391384 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: Mary Haas | Statement: [Morris Swadesh, spouse, Mary Haas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Haas
Context triple: [Morris Swadesh, spouse, Mary Haas]
  • A. Mary Haas chosen
    Mary Haas was an influential American linguist renowned for her work on Native American languages and for training a generation of field linguists in the Boasian tradition.
  • B. Betty Haas
    Betty Haas is known as the former wife of American politician and longtime U.S. Senator Joe Lieberman.
  • C. Mary Genevieve Laufersweiler
    Mary Genevieve Laufersweiler was the mother of American hotel magnate Conrad Hilton and a formative influence on his early life and values.
  • D. Mary Rommely
    Mary Rommely is the deeply religious, old-world immigrant grandmother in Betty Smith’s novel "A Tree Grows in Brooklyn," known for her enduring faith and influence on her daughter Katie Nolan and granddaughter Francie.
  • E. Anne Schaefer
    Anne Schaefer was an American silent film actress active in the early 20th century, appearing in numerous productions during the 1910s and 1920s.
  • 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_69c687e7b8688190811ffee72e096468 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6aed289448190a13c77085bccb006 completed March 27, 2026, 4:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c72f7450dc8190881a9347b8b9475f completed March 28, 2026, 1:31 a.m.
Created at: March 27, 2026, 1:55 p.m.