Triple

T8060224
Position Surface form Disambiguated ID Type / Status
Subject EA Sports E188100 entity
Predicate hasFranchise P13614 FINISHED
Object NBA Live E89743 NE FINISHED

How this triple was built (2 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: NBA Live | Statement: [EA Sports, hasFranchise, NBA Live]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: NBA Live
Context triple: [EA Sports, hasFranchise, NBA Live]
  • A. NBA Live chosen
    NBA Live is a basketball video game series developed and published by EA Sports that simulates National Basketball Association gameplay.
  • B. NBA 2K
    NBA 2K is a long-running basketball video game series that simulates the NBA with realistic gameplay, teams, and players.
  • C. NFL 2K
    NFL 2K is a critically acclaimed American football video game series known for its realistic gameplay and as a major competitor to EA Sports' Madden NFL franchise in the early 2000s.
  • D. NHL 2K
    NHL 2K is an ice hockey video game series known for its realistic simulation gameplay and was a prominent competitor to EA Sports' NHL franchise.
  • E. NBA Jam
    NBA Jam is a classic arcade-style basketball video game known for its over-the-top dunks, fast-paced two-on-two gameplay, and iconic catchphrases.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca82b2f68881908c50560697e210da completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3fcaa8b8819099267564b6542547 completed March 31, 2026, 3:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc63d6484c8190b2fd2c2bef179fc4 completed April 1, 2026, 12:16 a.m.
Created at: March 30, 2026, 5:25 p.m.