Triple

T10551377
Position Surface form Disambiguated ID Type / Status
Subject Limoges – Bellegarde Airport E248954 entity
Predicate IATAcode P418 FINISHED
Object LIG
LIG is the IATA airport code for Limoges – Bellegarde Airport in Limoges, France.
E870261 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: LIG | Statement: [Limoges – Bellegarde Airport, IATAcode, LIG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: LIG
Context triple: [Limoges – Bellegarde Airport, IATAcode, LIG]
  • A. Liga
    Liga is the Spanish name commonly used to refer to the Catholic League, a powerful alliance of Catholic states formed during the French Wars of Religion to oppose Protestant influence.
  • B. Ligatne
    Ligatne is a small town in Latvia known for its scenic location within the Gauja National Park and its historic paper mill heritage.
  • C. I liga
    I liga is the second-highest tier of professional football in the Polish league system, sitting just below the Ekstraklasa.
  • D. LGK
    LGK is the IATA airport code for Langkawi International Airport, the main air gateway to the Langkawi archipelago in Malaysia.
  • E. Liguilla
    Liguilla is the postseason playoff phase of Mexico’s top-flight football league, Liga MX, in which the season’s champion is decided.
  • 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: LIG
Triple: [Limoges – Bellegarde Airport, IATAcode, LIG]
Generated description
LIG is the IATA airport code for Limoges – Bellegarde Airport in Limoges, France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: LIG
Target entity description: LIG is the IATA airport code for Limoges – Bellegarde Airport in Limoges, France.
  • A. Liga
    Liga is the Spanish name commonly used to refer to the Catholic League, a powerful alliance of Catholic states formed during the French Wars of Religion to oppose Protestant influence.
  • B. Ligatne
    Ligatne is a small town in Latvia known for its scenic location within the Gauja National Park and its historic paper mill heritage.
  • C. I liga
    I liga is the second-highest tier of professional football in the Polish league system, sitting just below the Ekstraklasa.
  • D. LGK
    LGK is the IATA airport code for Langkawi International Airport, the main air gateway to the Langkawi archipelago in Malaysia.
  • E. Liguilla
    Liguilla is the postseason playoff phase of Mexico’s top-flight football league, Liga MX, in which the season’s champion is decided.
  • 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_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d526d4c4048190a104d6e088f565b3 completed April 7, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69d934639b3481908204db41101132c3 completed April 10, 2026, 5:33 p.m.
NEDg Description generation batch_69d938c8b25c8190bb048053d8668e5c completed April 10, 2026, 5:52 p.m.
NED2 Entity disambiguation (via description) batch_69d939b1844881908c8fbcb9488863f6 completed April 10, 2026, 5:56 p.m.
Created at: April 6, 2026, 12:34 p.m.