Triple

T4572848
Position Surface form Disambiguated ID Type / Status
Subject Doncaster E123073 entity
Predicate twinTown P1072 FINISHED
Object Avion
Avion is a commune in the Pas-de-Calais department in northern France.
E454082 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: Avion | Statement: [Doncaster, twinTown, Avion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Avion
Context triple: [Doncaster, twinTown, Avion]
  • A. Aeroplan
    Aeroplan is Air Canada's loyalty program that allows members to earn and redeem points for flights, upgrades, and other travel-related rewards.
  • B. Autavia
    Autavia is a line of high-performance sports chronographs and watches by TAG Heuer, originally designed for automotive and aviation use.
  • C. Altior
    Altior is a celebrated British National Hunt racehorse renowned for his exceptional unbeaten streak over fences and multiple Grade 1 victories.
  • D. Equair
    Equair is an Ecuadorian airline that operated domestic passenger flights, notably serving routes from Guayaquil and Quito.
  • E. The Spit
    The Spit is a sandy peninsula and recreational precinct on the Gold Coast in Queensland, Australia, known for its beaches, parklands, and major attractions.
  • 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: Avion
Triple: [Doncaster, twinTown, Avion]
Generated description
Avion is a commune in the Pas-de-Calais department in northern France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Avion
Target entity description: Avion is a commune in the Pas-de-Calais department in northern France.
  • A. Aeroplan
    Aeroplan is Air Canada's loyalty program that allows members to earn and redeem points for flights, upgrades, and other travel-related rewards.
  • B. Autavia
    Autavia is a line of high-performance sports chronographs and watches by TAG Heuer, originally designed for automotive and aviation use.
  • C. Altior
    Altior is a celebrated British National Hunt racehorse renowned for his exceptional unbeaten streak over fences and multiple Grade 1 victories.
  • D. Equair
    Equair is an Ecuadorian airline that operated domestic passenger flights, notably serving routes from Guayaquil and Quito.
  • E. The Spit
    The Spit is a sandy peninsula and recreational precinct on the Gold Coast in Queensland, Australia, known for its beaches, parklands, and major attractions.
  • 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_69bd46466c7081909d07f36be2d08804 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd58c711408190a2b096daf57e6eac completed March 20, 2026, 2:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdd3d709308190aeb6a71a9dabdd3c completed March 20, 2026, 11:10 p.m.
NEDg Description generation batch_69bdd49a9b2081909843c6c53ee1cbdc completed March 20, 2026, 11:13 p.m.
NED2 Entity disambiguation (via description) batch_69bdd513d36c81909958dabb1acbe094 completed March 20, 2026, 11:15 p.m.
Created at: March 20, 2026, 1:10 p.m.