Triple

T13260305
Position Surface form Disambiguated ID Type / Status
Subject Hokan (proposed) E315773 entity
Predicate studiedBy P1945 FINISHED
Object Mary R. Haas
Mary R. Haas was an influential American linguist renowned for her work on Native American languages and for training a generation of field linguists.
E1117019 NE FINISHED

How this triple was built (4 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 R. Haas | Statement: [Hokan (proposed), studiedBy, Mary R. Haas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary R. Haas
Context triple: [Hokan (proposed), studiedBy, Mary R. Haas]
  • A. Evelyn D. Haas
    Evelyn D. Haas was a prominent American philanthropist and arts patron, closely associated with major cultural and charitable initiatives in the San Francisco Bay Area.
  • B. Margaret C. Etter
    Margaret C. Etter was an influential American chemist and crystallographer known for pioneering work in hydrogen bonding and crystal engineering.
  • C. Mary M. Wyman
    Mary M. Wyman was the wife of influential American geographer and geologist William Morris Davis.
  • D. Dorothy C. Cressman
    Dorothy C. Cressman was the wife of American archaeologist and anthropologist Luther Cressman.
  • E. Mary M. Schroeder
    Mary M. Schroeder is an American jurist who served as a judge, and later chief judge, on the U.S. Court of Appeals for the Ninth Circuit.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mary R. Haas
Triple: [Hokan (proposed), studiedBy, Mary R. Haas]
Generated description
Mary R. Haas was an influential American linguist renowned for her work on Native American languages and for training a generation of field linguists.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary R. Haas
Target entity description: Mary R. Haas was an influential American linguist renowned for her work on Native American languages and for training a generation of field linguists.
  • A. Evelyn D. Haas
    Evelyn D. Haas was a prominent American philanthropist and arts patron, closely associated with major cultural and charitable initiatives in the San Francisco Bay Area.
  • B. Margaret C. Etter
    Margaret C. Etter was an influential American chemist and crystallographer known for pioneering work in hydrogen bonding and crystal engineering.
  • C. Mary M. Wyman
    Mary M. Wyman was the wife of influential American geographer and geologist William Morris Davis.
  • D. Dorothy C. Cressman
    Dorothy C. Cressman was the wife of American archaeologist and anthropologist Luther Cressman.
  • E. Mary M. Schroeder
    Mary M. Schroeder is an American jurist who served as a judge, and later chief judge, on the U.S. Court of Appeals for the Ninth Circuit.
  • F. None of above. chosen

Provenance (5 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_69d806b1d9ac8190852c5571d5bd5f0f completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98f778088819082b8a596c04bfe02 completed April 11, 2026, 12:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69fdfb6b97888190923ce7a6e59ff752 completed May 8, 2026, 3:04 p.m.
NEDg Description generation batch_69fdffed6978819096b61adfe7eba2f0 completed May 8, 2026, 3:23 p.m.
NED2 Entity disambiguation (via description) batch_69fe00870b40819090cf6304272f714d completed May 8, 2026, 3:25 p.m.
Created at: April 9, 2026, 9:25 p.m.