Triple

T2485796
Position Surface form Disambiguated ID Type / Status
Subject RAF Ascension Island E55922 entity
Predicate IATACode P418 FINISHED
Object ASI
ASI is the IATA airport code for RAF Ascension Island, a military airfield on Ascension Island in the South Atlantic Ocean.
 E271148 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: ASI | Statement: [RAF Ascension Island, IATACode, ASI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ASI
Context triple: [RAF Ascension Island, IATACode, ASI]
  • A. ASI
    ASI (Agenzia Spaziale Italiana) is the Italian Space Agency responsible for coordinating Italy’s space policy, research, and missions in collaboration with international partners.
  • B. IAS
    IAS is India’s premier civil service responsible for administrative leadership and implementation of government policies at the central and state levels.
  • C. AS
    AS is the two-letter IATA airline designator assigned to Alaska Airlines, used in flight numbers and ticketing.
  • D. AS
    AS is the two-letter ISO 3166-1 alpha-2 country code assigned to American Samoa.
  • E. AS
    AS is the official vehicle registration code assigned to the Indian state of Assam.
  • 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: ASI
Triple: [RAF Ascension Island, IATACode, ASI]
Generated description
ASI is the IATA airport code for RAF Ascension Island, a military airfield on Ascension Island in the South Atlantic Ocean.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ASI
Target entity description: ASI is the IATA airport code for RAF Ascension Island, a military airfield on Ascension Island in the South Atlantic Ocean.
  • A. ASI
    ASI (Agenzia Spaziale Italiana) is the Italian Space Agency responsible for coordinating Italy’s space policy, research, and missions in collaboration with international partners.
  • B. IAS
    IAS is India’s premier civil service responsible for administrative leadership and implementation of government policies at the central and state levels.
  • C. AS
    AS is the two-letter IATA airline designator assigned to Alaska Airlines, used in flight numbers and ticketing.
  • D. AS
    AS is the two-letter ISO 3166-1 alpha-2 country code assigned to American Samoa.
  • E. AS
    AS is the official vehicle registration code assigned to the Indian state of Assam.
  • 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_69ab49e670a88190b928e08302381710 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd17705488190b90b1aa66dd25972 completed March 7, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69af17ba433481908eccda5c6c6246be completed March 9, 2026, 6:55 p.m.
NEDg Description generation batch_69af1bbf545081908e1e51b5c7e4a196 completed March 9, 2026, 7:13 p.m.
NED2 Entity disambiguation (via description) batch_69af1c9c35648190bdeab34ce4032d26 completed March 9, 2026, 7:16 p.m.
Created at: March 6, 2026, 9:45 p.m.