Triple

T17144774
Position Surface form Disambiguated ID Type / Status
Subject Takamatsu Airport E416061 entity
Predicate IATAcode P418 FINISHED
Object TAK
TAK is the IATA airport code for Takamatsu Airport in Kagawa Prefecture, Japan.
E1253278 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: TAK | Statement: [Takamatsu Airport, IATAcode, TAK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TAK
Context triple: [Takamatsu Airport, IATAcode, TAK]
  • A. TAK
    TAK is a Kurdish militant organization known for carrying out urban terrorist attacks in Turkey, often seen as a hardline offshoot or affiliate of the PKK.
  • B. Tak
    Tak is a mountainous province and town in northwestern Thailand known as a gateway to Myanmar and for its natural parks, waterfalls, and cross-border trade.
  • C. Takats
    Takats is a surname of Hungarian origin, commonly appearing as a simplified or anglicized spelling of "Takács."
  • D. Takanot
    Takanot are rabbinic enactments or decrees established to address communal needs and clarify or safeguard Jewish law within Rabbinic Judaism.
  • E. takin
    The takin is a large, muscular goat-antelope native to the eastern Himalayas and surrounding mountain ranges, known for its thick golden coat and distinctive Roman-nosed profile.
  • 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: TAK
Triple: [Takamatsu Airport, IATAcode, TAK]
Generated description
TAK is the IATA airport code for Takamatsu Airport in Kagawa Prefecture, Japan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TAK
Target entity description: TAK is the IATA airport code for Takamatsu Airport in Kagawa Prefecture, Japan.
  • A. TAK
    TAK is a Kurdish militant organization known for carrying out urban terrorist attacks in Turkey, often seen as a hardline offshoot or affiliate of the PKK.
  • B. Tak
    Tak is a mountainous province and town in northwestern Thailand known as a gateway to Myanmar and for its natural parks, waterfalls, and cross-border trade.
  • C. Takats
    Takats is a surname of Hungarian origin, commonly appearing as a simplified or anglicized spelling of "Takács."
  • D. Takanot
    Takanot are rabbinic enactments or decrees established to address communal needs and clarify or safeguard Jewish law within Rabbinic Judaism.
  • E. takin
    The takin is a large, muscular goat-antelope native to the eastern Himalayas and surrounding mountain ranges, known for its thick golden coat and distinctive Roman-nosed profile.
  • 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_69d886d15af4819092f92f8a129763e6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f2d8ca8c81909bba0cd6d60a4776 completed April 18, 2026, 9:08 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01415718c88190834fedae7b01ac69 completed May 11, 2026, 2:39 a.m.
NEDg Description generation batch_6a014529e7908190bab3e351cdc78c7c completed May 11, 2026, 2:55 a.m.
NED2 Entity disambiguation (via description) batch_6a014595ca108190ad1587287987fc01 completed May 11, 2026, 2:57 a.m.
Created at: April 10, 2026, 5:36 a.m.