Triple

T34230
Position Surface form Disambiguated ID Type / Status
Subject Whitney Houston E681 entity
Predicate familyName P18 FINISHED
Object Houston E15847 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: Houston | Statement: [Whitney Houston, familyName, Houston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Houston
Context triple: [Whitney Houston, familyName, Houston]
  • A. Houston chosen
    Houston is a major U.S. metropolis known for its energy industry, NASA’s Johnson Space Center, and its diverse, rapidly growing population.
  • B. Dallas
    Dallas is the early series of United States Supreme Court case reports compiled by Alexander J. Dallas, covering decisions from the late 18th century before the official U.S. Reports numbering began.
  • C. Dallas, Texas
    Dallas, Texas is a major metropolitan city in northern Texas known for its role as a commercial and cultural hub, particularly in finance, technology, and telecommunications.
  • D. Austin
    Austin is a major city in central Texas known for its vibrant live music scene, tech industry, and cultural diversity.
  • E. San Antonio
    San Antonio is a large, historic city in south-central Texas known for the Alamo, the River Walk, and its rich blend of Mexican and Texan culture.
  • 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_69a2479dec388190967ba648663442c9 completed Feb. 28, 2026, 1:40 a.m.
NER Named-entity recognition batch_69a2487952bc8190a94ce39c70799c70 completed Feb. 28, 2026, 1:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2d4c4fcfc8190bdb6eea9fcb3f1b7 completed Feb. 28, 2026, 11:43 a.m.
Created at: Feb. 28, 2026, 1:44 a.m.