Triple

T3766087
Position Surface form Disambiguated ID Type / Status
Subject 1998 FIFA World Cup E82680 entity
Predicate mascot P52 FINISHED
Object Footix
Footix is the anthropomorphic rooster character that served as the official mascot of the 1998 FIFA World Cup in France.
E386843 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: Footix | Statement: [1998 FIFA World Cup, mascot, Footix]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Footix
Context triple: [1998 FIFA World Cup, mascot, Footix]
  • A. Football Focus
    Football Focus is a long-running BBC television programme that provides previews, analysis, and discussion of football matches and news.
  • B. NFFN
    NFFN is the ICAO airport code for Nadi International Airport, the main international gateway to Fiji located on the island of Viti Levu.
  • C. Premier League Live
    Premier League Live is NBC Sports’ studio show providing pre-match, halftime, and post-match coverage, analysis, and commentary for English Premier League soccer broadcasts.
  • D. FPL
    FPL was a major Marxist-Leninist guerrilla organization in El Salvador that later became one of the principal components of the FMLN.
  • E. Sports Info Solutions
    Sports Info Solutions is a baseball analytics company known for its advanced defensive metrics, data-driven scouting, and publication of influential sabermetric research.
  • 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: Footix
Triple: [1998 FIFA World Cup, mascot, Footix]
Generated description
Footix is the anthropomorphic rooster character that served as the official mascot of the 1998 FIFA World Cup in France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Footix
Target entity description: Footix is the anthropomorphic rooster character that served as the official mascot of the 1998 FIFA World Cup in France.
  • A. Football Focus
    Football Focus is a long-running BBC television programme that provides previews, analysis, and discussion of football matches and news.
  • B. NFFN
    NFFN is the ICAO airport code for Nadi International Airport, the main international gateway to Fiji located on the island of Viti Levu.
  • C. Premier League Live
    Premier League Live is NBC Sports’ studio show providing pre-match, halftime, and post-match coverage, analysis, and commentary for English Premier League soccer broadcasts.
  • D. FPL
    FPL was a major Marxist-Leninist guerrilla organization in El Salvador that later became one of the principal components of the FMLN.
  • E. Sports Info Solutions
    Sports Info Solutions is a baseball analytics company known for its advanced defensive metrics, data-driven scouting, and publication of influential sabermetric research.
  • 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_69ad8b207b0081909d2b48843fbd8795 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcbfeb52081909c38103beb5dbdcd completed March 8, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4e5221ab08190a3599afbbd5dbc6e completed March 14, 2026, 4:33 a.m.
NEDg Description generation batch_69b4e5f07c7081908e1aae715984aac4 completed March 14, 2026, 4:37 a.m.
NED2 Entity disambiguation (via description) batch_69b4e6531b48819083c0d14c2ca4f7c1 completed March 14, 2026, 4:38 a.m.
Created at: March 8, 2026, 3:35 p.m.