Triple

T16105834
Position Surface form Disambiguated ID Type / Status
Subject Yen Tan E390735 entity
Predicate workLocation P7 FINISHED
Object Dallas E879379 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: Dallas | Statement: [Yen Tan, workLocation, Dallas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dallas
Context triple: [Yen Tan, workLocation, Dallas]
  • A. 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.
  • B. Dallas
    Dallas is a small borough in northeastern Pennsylvania known as part of the suburban and educational hub of the Wyoming Valley near Wilkes-Barre.
  • C. Dallas
    Dallas is a popular American comic strip created by cartoonist Jim Davis.
  • D. Dallas chosen
    Dallas is a major city in northern Texas known for its role as a commercial and cultural hub, particularly in finance, technology, and the energy industry.
  • E. Dallas
    Dallas is a character appearing in the "Home Invasion" storyline.
  • 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_69d87f1a8dd881909f1de6ef78849874 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1ff6d81d081909e1315f4dbfd7369 completed April 17, 2026, 9:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff28f63c88190968ecbd4706b1331 completed May 10, 2026, 2:50 a.m.
Created at: April 10, 2026, 5 a.m.