Triple

T6830555
Position Surface form Disambiguated ID Type / Status
Subject San Andros Airport E157125 entity
Predicate IATAcode P418 FINISHED
Object SAQ
SAQ is the IATA airport code for San Andros Airport, a regional airport serving San Andros in the Bahamas.
E621042 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: SAQ | Statement: [San Andros Airport, IATAcode, SAQ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SAQ
Context triple: [San Andros Airport, IATAcode, SAQ]
  • A. BAQ
    BAQ is the station code for Baquedano, a transit station in Chile’s transportation network.
  • B. SA1
    SA1 is a 3GPP working group responsible for defining overall service requirements and use cases for mobile telecommunications systems.
  • C. SA1
    SA1 is a powerful coprocessor chip used in certain Super Nintendo Entertainment System game cartridges to enhance processing speed and add advanced features beyond the console’s base hardware.
  • D. SATI
    SATI is an engineering and technology-focused institute in India formally known as Samrat Ashok Technological Institute.
  • E. SACT
    SACT is the Supreme Allied Commander Transformation, the NATO strategic commander responsible for leading the alliance’s military transformation and capability development.
  • 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: SAQ
Triple: [San Andros Airport, IATAcode, SAQ]
Generated description
SAQ is the IATA airport code for San Andros Airport, a regional airport serving San Andros in the Bahamas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SAQ
Target entity description: SAQ is the IATA airport code for San Andros Airport, a regional airport serving San Andros in the Bahamas.
  • A. BAQ
    BAQ is the station code for Baquedano, a transit station in Chile’s transportation network.
  • B. SA1
    SA1 is a 3GPP working group responsible for defining overall service requirements and use cases for mobile telecommunications systems.
  • C. SA1
    SA1 is a powerful coprocessor chip used in certain Super Nintendo Entertainment System game cartridges to enhance processing speed and add advanced features beyond the console’s base hardware.
  • D. SATI
    SATI is an engineering and technology-focused institute in India formally known as Samrat Ashok Technological Institute.
  • E. SACT
    SACT is the Supreme Allied Commander Transformation, the NATO strategic commander responsible for leading the alliance’s military transformation and capability development.
  • 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_69c6882a5b5c8190917a7db9ed36bad1 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d62820808190ad3c244893e88699 completed March 27, 2026, 7:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c723f73eec81908c666888a19c0b29 completed March 28, 2026, 12:42 a.m.
NEDg Description generation batch_69c725139d748190ba9588c31b5188bd completed March 28, 2026, 12:47 a.m.
NED2 Entity disambiguation (via description) batch_69c725749efc8190b00fb7f2e44150dd completed March 28, 2026, 12:48 a.m.
Created at: March 27, 2026, 2:18 p.m.