Triple

T7794048
Position Surface form Disambiguated ID Type / Status
Subject Tezpur Airport E180252 entity
Predicate IATAcode P418 FINISHED
Object TEZ
TEZ is the IATA airport code for Tezpur Airport, a domestic airport serving the city of Tezpur in Assam, India.
 E693965 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: TEZ | Statement: [Tezpur Airport, IATAcode, TEZ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TEZ
Context triple: [Tezpur Airport, IATAcode, TEZ]
  • A. TEB
    TEB is the IATA airport code for Teterboro Airport, a major general aviation and corporate jet airport serving the New York City metropolitan area in New Jersey.
  • B. Taze
    Taze is the middle name of Charles Taze Russell, the American religious leader who founded the Bible Student movement and was an early influence on Jehovah’s Witnesses.
  • C. Zeen
    Zeen was a web-based publishing tool that allowed users to easily create and share digital magazines and visual stories online.
  • D. TEV
    TEV is a modern, easy-to-read English translation of the Bible, also known as the Today’s English Version or Good News Bible.
  • E. Tegsedi
    Tegsedi is an antisense oligonucleotide drug used to treat hereditary transthyretin-mediated amyloidosis by reducing the production of the transthyretin protein.
  • 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: TEZ
Triple: [Tezpur Airport, IATAcode, TEZ]
Generated description
TEZ is the IATA airport code for Tezpur Airport, a domestic airport serving the city of Tezpur in Assam, India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TEZ
Target entity description: TEZ is the IATA airport code for Tezpur Airport, a domestic airport serving the city of Tezpur in Assam, India.
  • A. TEB
    TEB is the IATA airport code for Teterboro Airport, a major general aviation and corporate jet airport serving the New York City metropolitan area in New Jersey.
  • B. Taze
    Taze is the middle name of Charles Taze Russell, the American religious leader who founded the Bible Student movement and was an early influence on Jehovah’s Witnesses.
  • C. Zeen
    Zeen was a web-based publishing tool that allowed users to easily create and share digital magazines and visual stories online.
  • D. TEV
    TEV is a modern, easy-to-read English translation of the Bible, also known as the Today’s English Version or Good News Bible.
  • E. Tegsedi
    Tegsedi is an antisense oligonucleotide drug used to treat hereditary transthyretin-mediated amyloidosis by reducing the production of the transthyretin protein.
  • 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_69ca827d22208190b4dc5aa680edcf5d completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cae939c7388190b36d3e746be27a4d completed March 30, 2026, 9:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69cb13dbe1f88190bde2c5c76dcfeb8f completed March 31, 2026, 12:22 a.m.
NEDg Description generation batch_69cb1730900c8190bc0322c4b6a3772f completed March 31, 2026, 12:37 a.m.
NED2 Entity disambiguation (via description) batch_69cb1a3e6da08190bf4f82b59db41333 completed March 31, 2026, 12:50 a.m.
Created at: March 30, 2026, 4:31 p.m.