Triple

T2786643
Position Surface form Disambiguated ID Type / Status
Subject MRT subway E61825 entity
Predicate shortName P43 FINISHED
Object BEM
BEM is the abbreviated name of a station on the MRT subway system.
 E300204 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: BEM | Statement: [MRT subway, shortName, BEM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BEM
Context triple: [MRT subway, shortName, BEM]
  • A. BdM
    BdM is the central bank of Mexico, responsible for maintaining the country’s monetary stability and issuing its currency.
  • B. BES
    BES is the international vehicle registration code used for the Caribbean Netherlands islands of Bonaire, Sint Eustatius, and Saba.
  • C. BIE
    BIE is a U.S. federal agency within the Department of the Interior responsible for providing and overseeing education services for Native American students in schools on or near reservations.
  • D. BIE
    BIE is the commonly used acronym for the Bureau International des Expositions, the intergovernmental organization that oversees and regulates World Expos.
  • E. BEG
    BEG is the IATA airport code for Belgrade Nikola Tesla Airport, the main international airport serving Serbia’s capital city.
  • 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: BEM
Triple: [MRT subway, shortName, BEM]
Generated description
BEM is the abbreviated name of a station on the MRT subway system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BEM
Target entity description: BEM is the abbreviated name of a station on the MRT subway system.
  • A. BdM
    BdM is the central bank of Mexico, responsible for maintaining the country’s monetary stability and issuing its currency.
  • B. BES
    BES is the international vehicle registration code used for the Caribbean Netherlands islands of Bonaire, Sint Eustatius, and Saba.
  • C. BIE
    BIE is a U.S. federal agency within the Department of the Interior responsible for providing and overseeing education services for Native American students in schools on or near reservations.
  • D. BIE
    BIE is the commonly used acronym for the Bureau International des Expositions, the intergovernmental organization that oversees and regulates World Expos.
  • E. BEG
    BEG is the IATA airport code for Belgrade Nikola Tesla Airport, the main international airport serving Serbia’s capital city.
  • 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_69ab4b7f51d881908768300ebd2fbdae completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abddb0d3488190a3f2bf47ebb35802 completed March 7, 2026, 8:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc6526d0c81908df1710709cc5346 completed March 10, 2026, 7:20 a.m.
NEDg Description generation batch_69afc852c0988190bba816db0940139f completed March 10, 2026, 7:29 a.m.
NED2 Entity disambiguation (via description) batch_69afc8b333848190bf4bfbc31f9c5147 completed March 10, 2026, 7:30 a.m.
Created at: March 6, 2026, 9:57 p.m.