Triple

T19400758
Position Surface form Disambiguated ID Type / Status
Subject William T. Piper Memorial Airport E485315 entity
Predicate FAAIdentifier P420 FINISHED
Object LHV
LHV is the FAA location identifier for William T. Piper Memorial Airport, a public airport in Lock Haven, Pennsylvania named after the founder of Piper Aircraft.
E1373947 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: LHV | Statement: [William T. Piper Memorial Airport, FAAIdentifier, LHV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: LHV
Context triple: [William T. Piper Memorial Airport, FAAIdentifier, LHV]
  • A. LHF
    LHF is the governing body responsible for organizing and overseeing ice hockey activities and national teams in Latvia.
  • B. LHW
    LHW is the IATA airport code for Lanzhou Zhongchuan International Airport, the main air gateway serving Lanzhou in Gansu Province, China.
  • C. LSK/LV
    LSK/LV was the air force branch of the National People’s Army of the former East Germany, responsible for the country’s military aviation and air defense.
  • D. Levien
    Levien is a surname shared by various notable individuals across fields such as literature, film, and business.
  • E. Lasva
    Lasva is a small village located in southeastern Estonia within Võru County.
  • 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: LHV
Triple: [William T. Piper Memorial Airport, FAAIdentifier, LHV]
Generated description
LHV is the FAA location identifier for William T. Piper Memorial Airport, a public airport in Lock Haven, Pennsylvania named after the founder of Piper Aircraft.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: LHV
Target entity description: LHV is the FAA location identifier for William T. Piper Memorial Airport, a public airport in Lock Haven, Pennsylvania named after the founder of Piper Aircraft.
  • A. LHF
    LHF is the governing body responsible for organizing and overseeing ice hockey activities and national teams in Latvia.
  • B. LHW
    LHW is the IATA airport code for Lanzhou Zhongchuan International Airport, the main air gateway serving Lanzhou in Gansu Province, China.
  • C. LSK/LV
    LSK/LV was the air force branch of the National People’s Army of the former East Germany, responsible for the country’s military aviation and air defense.
  • D. Levien
    Levien is a surname shared by various notable individuals across fields such as literature, film, and business.
  • E. Lasva
    Lasva is a small village located in southeastern Estonia within Võru County.
  • 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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6257692508190b658928e224d72d7 completed April 20, 2026, 1:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a072b90e5b88190af351c9b1814a456 completed May 15, 2026, 2:20 p.m.
NEDg Description generation batch_6a072d79ae348190a078fb5441c6466b completed May 15, 2026, 2:28 p.m.
NED2 Entity disambiguation (via description) batch_6a072e930e948190ac19fa2b81639922 completed May 15, 2026, 2:32 p.m.
Created at: April 10, 2026, 1:36 p.m.