Triple

T11346266
Position Surface form Disambiguated ID Type / Status
Subject Tuluksak, Alaska E268720 entity
Predicate airportIATAcode P418 FINISHED
Object TLT
TLT is the IATA airport code for the small public airport serving the remote community of Tuluksak in western Alaska.
E920076 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: TLT | Statement: [Tuluksak, Alaska, airportIATAcode, TLT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TLT
Context triple: [Tuluksak, Alaska, airportIATAcode, TLT]
  • A. TLT
    TLT is the time zone abbreviation used for Timor Leste Time, the standard time observed in East Timor.
  • B. TLL
    TLL is the three-letter IATA airport code for Lennart Meri Tallinn Airport, the main international airport serving Tallinn, Estonia.
  • C. LT
    LT is a mid-level trim designation commonly used by Chevrolet to denote a better-equipped, more comfort- and feature-focused version of its vehicles.
  • D. LT
    LT is the abbreviated name for the Logic Theorist, an early computer program that pioneered automated theorem proving in mathematical logic.
  • E. TLA
    TLA is a formal specification language developed by Leslie Lamport for describing and reasoning about concurrent and distributed systems using temporal logic.
  • 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: TLT
Triple: [Tuluksak, Alaska, airportIATAcode, TLT]
Generated description
TLT is the IATA airport code for the small public airport serving the remote community of Tuluksak in western Alaska.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TLT
Target entity description: TLT is the IATA airport code for the small public airport serving the remote community of Tuluksak in western Alaska.
  • A. TLT
    TLT is the time zone abbreviation used for Timor Leste Time, the standard time observed in East Timor.
  • B. TLL
    TLL is the three-letter IATA airport code for Lennart Meri Tallinn Airport, the main international airport serving Tallinn, Estonia.
  • C. LT
    LT is a mid-level trim designation commonly used by Chevrolet to denote a better-equipped, more comfort- and feature-focused version of its vehicles.
  • D. LT
    LT is the abbreviated name for the Logic Theorist, an early computer program that pioneered automated theorem proving in mathematical logic.
  • E. TLA
    TLA is a formal specification language developed by Leslie Lamport for describing and reasoning about concurrent and distributed systems using temporal logic.
  • 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_69d6aacbe18081909e5fadb50082dd96 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea1f9574819089760c5b5908f09e completed April 9, 2026, 6:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5437fb1208190892fa6b05c92478e completed April 19, 2026, 9:05 p.m.
NEDg Description generation batch_69e548bb7be4819093aeeaf0c048033e completed April 19, 2026, 9:27 p.m.
NED2 Entity disambiguation (via description) batch_69e54eeba4a88190af128a99c277853a completed April 19, 2026, 9:53 p.m.
Created at: April 8, 2026, 9:33 p.m.