Triple

T13148059
Position Surface form Disambiguated ID Type / Status
Subject American Conservatory Theater E312391 entity
Predicate shortName P43 FINISHED
Object ACT
ACT is a renowned nonprofit theater company and acting school based in San Francisco, known for its professional productions and conservatory training programs.
 E1024664 NE FINISHED

How this triple was built (4 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: ACT | Statement: [American Conservatory Theater, shortName, ACT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ACT
Context triple: [American Conservatory Theater, shortName, ACT]
  • A. ACT
    ACT is a standardized college admissions test in the United States that assesses high school students' readiness for college-level work.
  • B. ACT
    ACT is the National Rail station code used to identify Acton Town railway station in the United Kingdom’s rail network.
  • C. ACT
    ACT is the standard vehicle registration code used for the Australian Capital Territory in Australia.
  • D. ACT
    ACT is NATO’s strategic command responsible for leading the alliance’s military transformation, innovation, and future capability development.
  • E. Act
    Act was a short-lived late-1980s synth-pop duo featuring Thomas Leer and Claudia Brücken, known for their sophisticated, theatrical electronic sound and association with the ZTT label.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: ACT
Triple: [American Conservatory Theater, shortName, ACT]
Generated description
ACT is a renowned nonprofit theater company and acting school based in San Francisco, known for its professional productions and conservatory training programs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ACT
Target entity description: ACT is a renowned nonprofit theater company and acting school based in San Francisco, known for its professional productions and conservatory training programs.
  • A. ACT
    ACT is a standardized college admissions test in the United States that assesses high school students' readiness for college-level work.
  • B. ACT
    ACT is the standard vehicle registration code used for the Australian Capital Territory in Australia.
  • C. ACT
    ACT is NATO’s strategic command responsible for leading the alliance’s military transformation, innovation, and future capability development.
  • D. ACT
    ACT is the National Rail station code used to identify Acton Town railway station in the United Kingdom’s rail network.
  • E. Act
    Act was a short-lived late-1980s synth-pop duo featuring Thomas Leer and Claudia Brücken, known for their sophisticated, theatrical electronic sound and association with the ZTT label.
  • F. None of above. chosen

Provenance (5 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_69d806aabde48190899e13e41659cae5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98bd0f5b08190ab700c5de1c8e138 completed April 10, 2026, 11:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eae834908190aecb825db1d705ff completed May 3, 2026, 6:27 a.m.
NEDg Description generation batch_69f6eb9ff2a881908004cc060b892f48 completed May 3, 2026, 6:30 a.m.
NED2 Entity disambiguation (via description) batch_69f6ec67be70819087d6c49a85d163bc completed May 3, 2026, 6:34 a.m.
Created at: April 9, 2026, 9:10 p.m.