Triple

T16855723
Position Surface form Disambiguated ID Type / Status
Subject Asahi Glass Co., Ltd. E409776 entity
Predicate brand P1500 FINISHED
Object AGC
AGC is a leading Japanese manufacturer known worldwide for its glass, electronics, chemicals, and high-tech materials used in buildings, automobiles, and various industrial applications.
 E1237573 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: AGC | Statement: [Asahi Glass Co., Ltd., brand, AGC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AGC
Context triple: [Asahi Glass Co., Ltd., brand, AGC]
  • A. AGC
    AGC is a family of modern French regional multiple-unit trains built by Bombardier for versatile operation on TER networks.
  • B. AGC
    AGC is the Indian Railways station code for Agra Cantonment railway station, the main rail hub serving the city of Agra in Uttar Pradesh, India.
  • C. AGC
    AGC is an international treaty that coordinates and standardizes the main railway lines across Europe to facilitate efficient cross-border rail transport.
  • D. AGC
    AGC is the three-letter IATA airport code assigned to Allegheny County Airport near Pittsburgh, Pennsylvania.
  • E. AGC
    AGC is the stock ticker symbol for Altimeter Growth Corp, a special purpose acquisition company (SPAC) associated with Altimeter Capital.
  • 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: AGC
Triple: [Asahi Glass Co., Ltd., brand, AGC]
Generated description
AGC is a leading Japanese manufacturer known worldwide for its glass, electronics, chemicals, and high-tech materials used in buildings, automobiles, and various industrial applications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AGC
Target entity description: AGC is a leading Japanese manufacturer known worldwide for its glass, electronics, chemicals, and high-tech materials used in buildings, automobiles, and various industrial applications.
  • A. AGC
    AGC is the stock ticker symbol for Altimeter Growth Corp, a special purpose acquisition company (SPAC) associated with Altimeter Capital.
  • B. AGC
    AGC is a family of modern French regional multiple-unit trains built by Bombardier for versatile operation on TER networks.
  • C. AGC
    AGC is the abbreviation for the Adjutant General's Corps, a branch of the British Army responsible for personnel administration, career management, and support services.
  • D. AGC
    AGC is an international treaty that coordinates and standardizes the main railway lines across Europe to facilitate efficient cross-border rail transport.
  • E. AGC
    AGC is the Indian Railways station code for Agra Cantonment railway station, the main rail hub serving the city of Agra in Uttar Pradesh, India.
  • 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_69d88395e6c88190b22730f335107c14 completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b37d69a08190af18b421066f44f1 completed April 18, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c2a6f2c48190874839f78f943fdb completed May 10, 2026, 5:38 p.m.
NEDg Description generation batch_6a00c3812c5881908e5c897a5b824e26 completed May 10, 2026, 5:42 p.m.
NED2 Entity disambiguation (via description) batch_6a00c3f62f3881909dc5665db8433063 completed May 10, 2026, 5:44 p.m.
Created at: April 10, 2026, 5:24 a.m.