Triple

T19977884
Position Surface form Disambiguated ID Type / Status
Subject Sharpstown E493738 entity
Predicate developer P73 FINISHED
Object Frank Sharp NE NERFINISHED

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: Frank Sharp | Statement: [Sharpstown, developer, Frank Sharp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Sharp
Context triple: [Sharpstown, developer, Frank Sharp]
  • A. Frank Sharp chosen
    Frank Sharp was an American real estate developer and businessman best known for creating the Sharpstown community in Houston, Texas.
  • B. William Read Scurry
    William Read Scurry was a 19th-century American military officer and Texas politician best known for his service as a Confederate general during the American Civil War.
  • C. William Terrell
    William Terrell was an American politician and public figure from Georgia, honored as the namesake of Terrell County.
  • D. William Ragsdale
    William Ragsdale is an American actor best known for his lead role in the 1985 horror-comedy film "Fright Night" and its sequel.
  • E. Isham Randolph
    Isham Randolph was an 18th-century Virginia planter and sea captain, best known as the grandfather of U.S. President Thomas Jefferson.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d1054e08190993b92b86ec5bbc8 completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:27 p.m.