Triple

T7103145
Position Surface form Disambiguated ID Type / Status
Subject Tambolaka Airport E165508 entity
Predicate icaoCode P419 FINISHED
Object WADT
WADT is the ICAO airport code for Tambolaka Airport, a regional airport serving the island of Sumba in Indonesia.
 E642378 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: WADT | Statement: [Tambolaka Airport, icaoCode, WADT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: WADT
Context triple: [Tambolaka Airport, icaoCode, WADT]
  • A. WADW
    WADW is the ICAO airport code for Umbu Mehang Kunda Airport in Indonesia.
  • B. WAT
    WAT is the National Rail station code for London Waterloo, one of the busiest and most important railway terminals in the United Kingdom.
  • C. WAWA
    WAWA is the station code for Wawa railway station, a train stop located in Wawa, New South Wales, Australia.
  • D. WADC
    WADC is the commonly used abbreviation for the World Anti-Doping Code, the core document that harmonizes anti-doping policies and regulations in global sport.
  • E. W&A
    W&A is the commonly used abbreviation for the Western and Atlantic Railroad, a historic rail line in the southeastern United States.
  • 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: WADT
Triple: [Tambolaka Airport, icaoCode, WADT]
Generated description
WADT is the ICAO airport code for Tambolaka Airport, a regional airport serving the island of Sumba in Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: WADT
Target entity description: WADT is the ICAO airport code for Tambolaka Airport, a regional airport serving the island of Sumba in Indonesia.
  • A. WADW
    WADW is the ICAO airport code for Umbu Mehang Kunda Airport in Indonesia.
  • B. WAT
    WAT is the National Rail station code for London Waterloo, one of the busiest and most important railway terminals in the United Kingdom.
  • C. WAWA
    WAWA is the station code for Wawa railway station, a train stop located in Wawa, New South Wales, Australia.
  • D. WADC
    WADC is the commonly used abbreviation for the World Anti-Doping Code, the core document that harmonizes anti-doping policies and regulations in global sport.
  • E. W&A
    W&A is the commonly used abbreviation for the Western and Atlantic Railroad, a historic rail line in the southeastern United States.
  • 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_69c6887fcddc8190a5d58908f6dee590 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e58a0a2c819088e0c8874fb4491f completed March 27, 2026, 8:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79cad60788190bb2b17d1c3f8e1cc completed March 28, 2026, 9:17 a.m.
NEDg Description generation batch_69c79d72dd70819084a4bf7e72865ed9 completed March 28, 2026, 9:20 a.m.
NED2 Entity disambiguation (via description) batch_69c79e12a40c8190b21128e17c3e212e completed March 28, 2026, 9:23 a.m.
Created at: March 27, 2026, 2:42 p.m.