Triple

T2463037
Position Surface form Disambiguated ID Type / Status
Subject Highlanders F.C. E54577 entity
Predicate rival P437 FINISHED
Object Caps United F.C.
Caps United F.C. is one of Zimbabwe’s most prominent football clubs, known for its passionate fan base and intense domestic rivalries.
 E268370 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: Caps United F.C. | Statement: [Highlanders F.C., rival, Caps United F.C.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Caps United F.C.
Context triple: [Highlanders F.C., rival, Caps United F.C.]
  • A. Incheon United FC
    Incheon United FC is a professional South Korean football club based in the city of Incheon that competes in the K League.
  • B. Daejeon Hana Citizen FC
    Daejeon Hana Citizen FC is a professional South Korean football club based in the city of Daejeon that competes in the K League system.
  • C. Daegu FC
    Daegu FC is a professional South Korean football club based in Daegu that competes in the K League.
  • D. Albirex Niigata
    Albirex Niigata is a professional Japanese football club based in Niigata that competes in the J.League.
  • E. Vissel Kobe
    Vissel Kobe is a professional Japanese football club based in Kobe that competes in the J1 League.
  • 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: Caps United F.C.
Triple: [Highlanders F.C., rival, Caps United F.C.]
Generated description
Caps United F.C. is one of Zimbabwe’s most prominent football clubs, known for its passionate fan base and intense domestic rivalries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Caps United F.C.
Target entity description: Caps United F.C. is one of Zimbabwe’s most prominent football clubs, known for its passionate fan base and intense domestic rivalries.
  • A. Incheon United FC
    Incheon United FC is a professional South Korean football club based in the city of Incheon that competes in the K League.
  • B. Daejeon Hana Citizen FC
    Daejeon Hana Citizen FC is a professional South Korean football club based in the city of Daejeon that competes in the K League system.
  • C. Daegu FC
    Daegu FC is a professional South Korean football club based in Daegu that competes in the K League.
  • D. Albirex Niigata
    Albirex Niigata is a professional Japanese football club based in Niigata that competes in the J.League.
  • E. Vissel Kobe
    Vissel Kobe is a professional Japanese football club based in Kobe that competes in the J1 League.
  • 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_69ab49dee84c819096b50a0049c347ac completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd11f093c8190877db3026d430bd5 completed March 7, 2026, 7:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69aef0d561a081909310113658b98f12 completed March 9, 2026, 4:09 p.m.
NEDg Description generation batch_69aef8380d24819092b6502117a8ed42 completed March 9, 2026, 4:41 p.m.
NED2 Entity disambiguation (via description) batch_69aef936b86c81908573ea73314fe6a9 completed March 9, 2026, 4:45 p.m.
Created at: March 6, 2026, 9:44 p.m.