Triple

T20691194
Position Surface form Disambiguated ID Type / Status
Subject ANZ National Stadium E508553 entity
Predicate tenants P3277 FINISHED
Object Suva F.C.
Suva F.C. is a professional football club based in Suva, Fiji, competing in the country’s top-tier league and domestic cup competitions.
 E1445361 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: Suva F.C. | Statement: [ANZ National Stadium, tenants, Suva F.C.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Suva F.C.
Context triple: [ANZ National Stadium, tenants, Suva F.C.]
  • A. Navua F.C.
    Navua F.C. is a Fijian football club that competes in the country’s national soccer competitions.
  • B. Saipa FC
    Saipa FC is an Iranian professional football club based in Tehran, known for competing in the country’s top division and for its association with the Saipa automotive company.
  • C. Lae City FC
    Lae City FC is a professional football club based in Lae, Papua New Guinea, known as one of the country's leading teams in domestic competitions.
  • D. Auckland United FC
    Auckland United FC is a New Zealand football club based in Auckland that competes in the country's Northern League.
  • E. Senrab F.C.
    Senrab F.C. is a renowned East London youth football club famous for producing numerous top-level professional players, including several future England internationals.
  • 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: Suva F.C.
Triple: [ANZ National Stadium, tenants, Suva F.C.]
Generated description
Suva F.C. is a professional football club based in Suva, Fiji, competing in the country’s top-tier league and domestic cup competitions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Suva F.C.
Target entity description: Suva F.C. is a professional football club based in Suva, Fiji, competing in the country’s top-tier league and domestic cup competitions.
  • A. Navua F.C.
    Navua F.C. is a Fijian football club that competes in the country’s national soccer competitions.
  • B. Saipa FC
    Saipa FC is an Iranian professional football club based in Tehran, known for competing in the country’s top division and for its association with the Saipa automotive company.
  • C. Lae City FC
    Lae City FC is a professional football club based in Lae, Papua New Guinea, known as one of the country's leading teams in domestic competitions.
  • D. Auckland United FC
    Auckland United FC is a New Zealand football club based in Auckland that competes in the country's Northern League.
  • E. Senrab F.C.
    Senrab F.C. is a renowned East London youth football club famous for producing numerous top-level professional players, including several future England internationals.
  • 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_69e0b4c1ed408190b72dd26b1e33f8a1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c10d83548190a52b9ef84c8f9205 completed April 21, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08d7e43a3c81909f63e63e30e9c435 completed May 16, 2026, 8:47 p.m.
NEDg Description generation batch_6a08d91216bc8190909e0e37f6d5e612 completed May 16, 2026, 8:52 p.m.
NED2 Entity disambiguation (via description) batch_6a08d99214b48190b0ffba4026d3fa39 completed May 16, 2026, 8:54 p.m.
Created at: April 16, 2026, 12:08 p.m.