Triple

T18060286
Position Surface form Disambiguated ID Type / Status
Subject Lashio Airport E432152 entity
Predicate IATA code P2569 FINISHED
Object LSH
LSH is the three-letter IATA airport code assigned to Lashio Airport in Myanmar.
 E1304344 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: LSH | Statement: [Lashio Airport, IATA code, LSH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LSH
Context triple: [Lashio Airport, IATA code, LSH]
  • A. LSM
    LSM is an undergraduate dual-degree program at the University of Pennsylvania that integrates rigorous training in life sciences with business and management education.
  • B. LLE
    LLE is the station code for Loulé railway station in Portugal’s Algarve region.
  • C. LSL
    LSL is the currency code for the Lesotho loti, the official monetary unit of Lesotho.
  • D. LCS
    LCS is the commonly used abbreviation for Lakefield College School, a Canadian independent boarding and day school known for its scenic campus and outdoor education focus.
  • E. LCS
    LCS is North America's premier professional League of Legends esports league, featuring top teams competing in seasonal splits and playoffs.
  • 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: LSH
Triple: [Lashio Airport, IATA code, LSH]
Generated description
LSH is the three-letter IATA airport code assigned to Lashio Airport in Myanmar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LSH
Target entity description: LSH is the three-letter IATA airport code assigned to Lashio Airport in Myanmar.
  • A. LSM
    LSM is an undergraduate dual-degree program at the University of Pennsylvania that integrates rigorous training in life sciences with business and management education.
  • B. LLE
    LLE is the station code for Loulé railway station in Portugal’s Algarve region.
  • C. LSL
    LSL is the currency code for the Lesotho loti, the official monetary unit of Lesotho.
  • D. LCS
    LCS is North America's premier professional League of Legends esports league, featuring top teams competing in seasonal splits and playoffs.
  • E. LCS
    LCS is the commonly used abbreviation for Lakefield College School, a Canadian independent boarding and day school known for its scenic campus and outdoor education focus.
  • 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4c10583648190a161c58abf4853d5 completed April 19, 2026, 11:48 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03566907988190aef2b0ceb2c9f4dc completed May 12, 2026, 4:33 p.m.
NEDg Description generation batch_6a03591fa4cc819084d1e50b7e5263cf completed May 12, 2026, 4:45 p.m.
NED2 Entity disambiguation (via description) batch_6a0359a3ead48190996d95ad5aaa2302 completed May 12, 2026, 4:47 p.m.
Created at: April 10, 2026, 10:26 a.m.