Triple

T5730575
Position Surface form Disambiguated ID Type / Status
Subject Martha Graham E126373 entity
Predicate givenName P17 FINISHED
Object Martha E49016 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: Martha | Statement: [Martha Graham, givenName, Martha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martha
Context triple: [Martha Graham, givenName, Martha]
  • A. Martha chosen
    Martha is a feminine given name of Aramaic origin, historically borne by notable figures such as Martha Washington, the first First Lady of the United States.
  • B. Martha Black
    Martha Black was a pioneering Canadian politician and naturalist, known as one of the first women elected to the Canadian Parliament and for her influential role in Yukon public life.
  • C. Bertha
    Bertha is a feminine given name of Germanic origin, historically associated with meanings like "bright" or "famous."
  • D. Bertha
    "Bertha" is a popular live staple and fan-favorite rock song by the Grateful Dead, first released on their 1971 self-titled live album (often called "Skull and Roses").
  • E. Bertha
    Bertha was a daughter of Charlemagne, the Frankish king and emperor who united much of Western Europe during the early Middle Ages.
  • 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_69c0082f723881908ce8bb13a0c0f8b7 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c025318d688190bd878c5aa1a28728 completed March 22, 2026, 5:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a8cca748190b471c842fd2ce218 completed March 22, 2026, 9:09 p.m.
Created at: March 22, 2026, 3:47 p.m.