Triple

T22691291
Position Surface form Disambiguated ID Type / Status
Subject Haiti national football team E561056 entity
Predicate fifaCode P6278 FINISHED
Object HAI
HAI is the FIFA country code used to represent the Haiti national football team in international football competitions and records.
 E1549354 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: HAI | Statement: [Haiti national football team, fifaCode, HAI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HAI
Context triple: [Haiti national football team, fifaCode, HAI]
  • A. HAA
    HAA is the Harvard Alumni Association, the organization that connects and serves Harvard University’s global community of alumni.
  • B. Haa
    Haa is the station code for Haarajoki railway station in Finland’s rail network.
  • C. Haiz
    Haiz is the debut extended play by American singer and actress Hailee Steinfeld, showcasing her transition into a pop music career.
  • D. HAC
    HAC is the acronym for Taiwan’s Hakka Affairs Council, a government body responsible for promoting and preserving Hakka culture and language.
  • E. HAV
    HAV is the IATA airport code for José Martí International Airport, the main international gateway serving Havana, Cuba.
  • 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: HAI
Triple: [Haiti national football team, fifaCode, HAI]
Generated description
HAI is the FIFA country code used to represent the Haiti national football team in international football competitions and records.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HAI
Target entity description: HAI is the FIFA country code used to represent the Haiti national football team in international football competitions and records.
  • A. HAA
    HAA is the Harvard Alumni Association, the organization that connects and serves Harvard University’s global community of alumni.
  • B. Haa
    Haa is the station code for Haarajoki railway station in Finland’s rail network.
  • C. Haiz
    Haiz is the debut extended play by American singer and actress Hailee Steinfeld, showcasing her transition into a pop music career.
  • D. HAC
    HAC is the acronym for Taiwan’s Hakka Affairs Council, a government body responsible for promoting and preserving Hakka culture and language.
  • E. HAV
    HAV is the IATA airport code for José Martí International Airport, the main international gateway serving Havana, Cuba.
  • 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1789adcc48190b4a717166d5dba19 completed April 29, 2026, 3:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b73fa5a648190b90ba303d1fe2397 completed May 18, 2026, 8:18 p.m.
NEDg Description generation batch_6a0b7755eb048190ba1657a9a09bc24b completed May 18, 2026, 8:32 p.m.
NED2 Entity disambiguation (via description) batch_6a0b780c0a4c8190b51b50c1e0e1a114 completed May 18, 2026, 8:35 p.m.
Created at: April 17, 2026, 3:13 p.m.