Triple

T18918155
Position Surface form Disambiguated ID Type / Status
Subject Gap Rapaces E462774 entity
Predicate league P888 FINISHED
Object Ligue Magnus
Ligue Magnus is the top professional ice hockey league in France, featuring the country’s leading clubs in the sport.
E1349899 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: Ligue Magnus | Statement: [Gap Rapaces, league, Ligue Magnus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ligue Magnus
Context triple: [Gap Rapaces, league, Ligue Magnus]
  • A. Milli Lig
    Milli Lig was the original name of Turkey’s top professional football league, which later became known as the Süper Lig.
  • B. Erovnuli Liga
    Erovnuli Liga is the top professional football division in Georgia, featuring the country’s leading clubs in its premier league competition.
  • C. Mestis
    Mestis is the second-highest level of professional ice hockey in Finland, sitting just below the top-tier Liiga.
  • D. Liga Națională
    Liga Națională is Romania’s top-tier professional basketball league, featuring the country’s leading clubs in national competition.
  • E. Bostik League
    The Bostik League is the sponsored name of the Isthmian League, a regional football league in England featuring semi-professional and amateur clubs from London and the South East.
  • 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: Ligue Magnus
Triple: [Gap Rapaces, league, Ligue Magnus]
Generated description
Ligue Magnus is the top professional ice hockey league in France, featuring the country’s leading clubs in the sport.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ligue Magnus
Target entity description: Ligue Magnus is the top professional ice hockey league in France, featuring the country’s leading clubs in the sport.
  • A. Milli Lig
    Milli Lig was the original name of Turkey’s top professional football league, which later became known as the Süper Lig.
  • B. Erovnuli Liga
    Erovnuli Liga is the top professional football division in Georgia, featuring the country’s leading clubs in its premier league competition.
  • C. Mestis
    Mestis is the second-highest level of professional ice hockey in Finland, sitting just below the top-tier Liiga.
  • D. Liga Națională
    Liga Națională is Romania’s top-tier professional basketball league, featuring the country’s leading clubs in national competition.
  • E. Bostik League
    The Bostik League is the sponsored name of the Isthmian League, a regional football league in England featuring semi-professional and amateur clubs from London and the South East.
  • 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_69d8dcfdbbb881909964fa5a75bd0b48 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c62884988190a362ada1a0a47134 completed April 20, 2026, 6:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0591165cbc8190a0aafbd6611c8095 completed May 14, 2026, 9:08 a.m.
NEDg Description generation batch_6a05965ab9a081909e430d9bef63c820 completed May 14, 2026, 9:31 a.m.
NED2 Entity disambiguation (via description) batch_6a0596c2ee4c8190b3b4db9afa4d1bed completed May 14, 2026, 9:32 a.m.
Created at: April 10, 2026, 11:59 a.m.