Triple

T1453823
Position Surface form Disambiguated ID Type / Status
Subject Istanbul Airport E31352 entity
Predicate ICAOcode P419 FINISHED
Object LTFM
LTFM is the ICAO airport code for Istanbul Airport, the main international airport serving Istanbul, Turkey.
E167309 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: LTFM | Statement: [Istanbul Airport, ICAOcode, LTFM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: LTFM
Context triple: [Istanbul Airport, ICAOcode, LTFM]
  • A. LTFJ
    LTFJ is the ICAO airport code for Istanbul Sabiha Gökçen International Airport, a major international airport serving the Asian side of Istanbul, Turkey.
  • B. LBF
    LBF is the IATA airport code for North Platte Regional Airport serving North Platte, Nebraska.
  • C. Tfng
    Tfng is the ISO 15924 four-letter code assigned to the Tifinagh script used for writing various Berber (Amazigh) languages.
  • D. LM
    LM is the IATA airline designator assigned to Loganair, a regional airline based in Scotland.
  • E. Fittja
    Fittja is a suburban district in the southern part of the Stockholm metropolitan area in Sweden, known for its diverse population and large-scale postwar housing.
  • 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: LTFM
Triple: [Istanbul Airport, ICAOcode, LTFM]
Generated description
LTFM is the ICAO airport code for Istanbul Airport, the main international airport serving Istanbul, Turkey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: LTFM
Target entity description: LTFM is the ICAO airport code for Istanbul Airport, the main international airport serving Istanbul, Turkey.
  • A. LTFJ
    LTFJ is the ICAO airport code for Istanbul Sabiha Gökçen International Airport, a major international airport serving the Asian side of Istanbul, Turkey.
  • B. LBF
    LBF is the IATA airport code for North Platte Regional Airport serving North Platte, Nebraska.
  • C. Tfng
    Tfng is the ISO 15924 four-letter code assigned to the Tifinagh script used for writing various Berber (Amazigh) languages.
  • D. LM
    LM is the IATA airline designator assigned to Loganair, a regional airline based in Scotland.
  • E. Fittja
    Fittja is a suburban district in the southern part of the Stockholm metropolitan area in Sweden, known for its diverse population and large-scale postwar housing.
  • 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_69a499171a28819085b993a3ac78e363 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c57e82d48190a30a4512f39f5de0 completed March 1, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad0e71ffd481909dfd0f77201dc17c completed March 8, 2026, 5:51 a.m.
NEDg Description generation batch_69ad0f6838bc8190b0a77eda44f1949e completed March 8, 2026, 5:55 a.m.
NED2 Entity disambiguation (via description) batch_69ad0fbdd20081909ea89e527a4e342e completed March 8, 2026, 5:57 a.m.
Created at: March 1, 2026, 8 p.m.