Triple

T14623772
Position Surface form Disambiguated ID Type / Status
Subject Julian Mandrake E343291 entity
Predicate basedIn P40 FINISHED
Object Austin, Texas E597342 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: Austin, Texas | Statement: [Julian Mandrake, basedIn, Austin, Texas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Austin, Texas
Context triple: [Julian Mandrake, basedIn, Austin, Texas]
  • A. City of Austin chosen
    The City of Austin is the capital of Texas, known for its vibrant live music scene, tech industry presence, and progressive cultural and political landscape.
  • B. 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.
  • C. Austin
    Austin is one of Chicago’s largest and most populous West Side community areas, known for its historic residential architecture and significant demographic and economic changes over time.
  • D. Austin
    Austin is a common English given name used for people of all genders, derived from the Latin name Augustine.
  • E. Austin
    Austin was an enslaved man held in bondage by George Washington who lived and labored at the President's House in Philadelphia during Washington's presidency.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb468acc4819083b7e818d5cec809 completed April 14, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdf078c1248190889ce04cffbf51dc completed May 8, 2026, 2:17 p.m.
Created at: April 10, 2026, 1:26 a.m.