Triple

T14346738
Position Surface form Disambiguated ID Type / Status
Subject Belém Air Base E355743 entity
Predicate hasIataCode P2569 FINISHED
Object BEL
BEL is the IATA airport code for the main airport serving Belém in the state of Pará, Brazil.
 E1093590 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: BEL | Statement: [Belém Air Base, hasIataCode, BEL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BEL
Context triple: [Belém Air Base, hasIataCode, BEL]
  • A. BEL
    BEL is the ICAO airline designator used to identify Brussels Airlines in international aviation operations.
  • B. BEL
    BEL is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Belgium in international standards and data systems.
  • C. BEL
    BEL is the commonly used abbreviation for Bharat Electronics Limited, an Indian state-owned aerospace and defense electronics company.
  • D. Bel
    Bel is a major Mesopotamian god, often identified with Marduk, revered as a supreme deity and lord of the heavens and earth in Babylonian religion.
  • E. BAL
    BAL is the Amtrak station code for Pennsylvania Station in Baltimore, Maryland, a major rail hub in the city’s transportation network.
  • 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: BEL
Triple: [Belém Air Base, hasIataCode, BEL]
Generated description
BEL is the IATA airport code for the main airport serving Belém in the state of Pará, Brazil.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BEL
Target entity description: BEL is the IATA airport code for the main airport serving Belém in the state of Pará, Brazil.
  • A. BEL
    BEL is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Belgium in international standards and data systems.
  • B. BEL
    BEL is the ICAO airline designator used to identify Brussels Airlines in international aviation operations.
  • C. BEL
    BEL is the commonly used abbreviation for Bharat Electronics Limited, an Indian state-owned aerospace and defense electronics company.
  • D. Bel
    Bel is a major Mesopotamian god, often identified with Marduk, revered as a supreme deity and lord of the heavens and earth in Babylonian religion.
  • E. BAL
    BAL is the commonly used acronym for the Basketball Africa League, a professional pan-African basketball competition organized in partnership with the NBA and FIBA.
  • 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_69d82790a7e08190877e2d349b2e8d8e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8e8b81bc8190ace2a575faf55cc0 completed April 14, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd469f63b881909c164b1aaadcc15d completed May 8, 2026, 2:12 a.m.
NEDg Description generation batch_69fd47bbc5e081908aa8b0e76661234f completed May 8, 2026, 2:17 a.m.
NED2 Entity disambiguation (via description) batch_69fd4840f0688190975d8c3c7eefb132 completed May 8, 2026, 2:19 a.m.
Created at: April 10, 2026, 1:14 a.m.