Triple

T18404322
Position Surface form Disambiguated ID Type / Status
Subject Shanklin Theatre E450080 entity
Predicate city P40 FINISHED
Object Evansville 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: Evansville | Statement: [Shanklin Theatre, city, Evansville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evansville
Context triple: [Shanklin Theatre, city, Evansville]
  • A. Evansville chosen
    Evansville is a major city in southwestern Indiana located along the Ohio River and serving as a regional economic and cultural hub.
  • B. Muncie
    Muncie is a mid-sized city in east-central Indiana known as the home of Ball State University and for its role as a classic American "Middletown" in sociological studies.
  • C. Atlanta, Indiana
    Atlanta, Indiana is a small rural town in central Indiana known for its close-knit community and annual New Earth Festival.
  • D. Indianapolis
    Indianapolis is the capital and most populous city of the U.S. state of Indiana, known for its major sports franchises and hosting the annual Indianapolis 500 auto race.
  • E. Richmond, Indiana
    Richmond, Indiana is a small city in eastern Indiana known historically as a regional transportation hub and for its contributions to early jazz recording and manufacturing.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e5195509cc8190bd4e91adb9b4a0ce completed April 19, 2026, 6:05 p.m.
Created at: April 10, 2026, 10:46 a.m.