Triple

T19107308
Position Surface form Disambiguated ID Type / Status
Subject Michael Martin E467688 entity
Predicate child P120 FINISHED
Object Mary Ann Martin
Mary Ann Martin is known as the daughter of Michael Martin.
E1368514 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 Ann Martin | Statement: [Michael Martin, child, Mary Ann Martin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Ann Martin
Context triple: [Michael Martin, child, Mary Ann Martin]
  • A. Mary Ann Parker
    Mary Ann Parker was the wife of Sir William Martin, the first Chief Justice of New Zealand, and a notable figure in early New Zealand colonial society.
  • B. Mary Ann Bernard
    Mary Ann Bernard is a film editor best known for her work on the biographical drama "Behind the Candelabra."
  • C. Martha Ann Smith
    Martha Ann Smith was a 19th-century Latter-day Saint woman best known as a daughter of early LDS Church leader and martyr Hyrum Smith.
  • D. Mary Ann Singleton
    Mary Ann Singleton is the naive yet determined young woman from Ohio who becomes a central figure navigating love, identity, and community in Armistead Maupin’s Tales of the City series set in 1970s San Francisco.
  • E. Mary Ann Benedict
    Mary Ann Benedict is a fictional character in the comedy film "Twins," known as the long-lost mother of the genetically engineered brothers Julius and Vincent Benedict.
  • 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 Ann Martin
Triple: [Michael Martin, child, Mary Ann Martin]
Generated description
Mary Ann Martin is known as the daughter of Michael Martin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary Ann Martin
Target entity description: Mary Ann Martin is known as the daughter of Michael Martin.
  • A. Mary Ann Parker
    Mary Ann Parker was the wife of Sir William Martin, the first Chief Justice of New Zealand, and a notable figure in early New Zealand colonial society.
  • B. Mary Ann Bernard
    Mary Ann Bernard is a film editor best known for her work on the biographical drama "Behind the Candelabra."
  • C. Martha Ann Smith
    Martha Ann Smith was a 19th-century Latter-day Saint woman best known as a daughter of early LDS Church leader and martyr Hyrum Smith.
  • D. Mary Ann Singleton
    Mary Ann Singleton is the naive yet determined young woman from Ohio who becomes a central figure navigating love, identity, and community in Armistead Maupin’s Tales of the City series set in 1970s San Francisco.
  • E. Mary Ann Benedict
    Mary Ann Benedict is a fictional character in the comedy film "Twins," known as the long-lost mother of the genetically engineered brothers Julius and Vincent Benedict.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e391245c8190b1393577b61c4f76 completed April 20, 2026, 8:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a07143c68708190b62a9c93ec6c6ce0 completed May 15, 2026, 12:40 p.m.
NEDg Description generation batch_6a0714c3099c81909b009fe952d0de81 completed May 15, 2026, 12:42 p.m.
NED2 Entity disambiguation (via description) batch_6a07152aafb48190a767005628c6380a completed May 15, 2026, 12:44 p.m.
Created at: April 10, 2026, 12:04 p.m.