Triple

T9630706
Position Surface form Disambiguated ID Type / Status
Subject Millerntor-Stadion E232794 entity
Predicate primaryCompetitionHosted P89354 FINISHED
Object 2. Bundesliga home matches LITERAL 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: 2. Bundesliga home matches | Statement: [Millerntor-Stadion, primaryCompetitionHosted, 2. Bundesliga home matches]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: primaryCompetitionHosted
Context triple: [Millerntor-Stadion, primaryCompetitionHosted, 2. Bundesliga home matches]
  • A. primaryCompetition
    Indicates that one entity is the main or most significant competitor of another within a given market, domain, or context.
  • B. primaryCompetitionCountry
    Indicates the main country in which an entity primarily conducts or participates in competitive activities or markets.
  • C. primaryCompetitionLevel
    Indicates the main or highest level of competition at which an entity primarily competes or operates.
  • D. hasCompetition
    Indicates that one entity is in a state of rivalry or contest with another entity, typically competing for the same goal, resource, or advantage.
  • E. qualifyingCompetitionFor
    Indicates that one competition serves as a qualifying event for participation in another competition.
  • F. None of above. chosen

Provenance (4 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_69ca848940cc8190b97cec654cb3bb4a completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9b01863c8190a9ec4684804f96bc completed April 1, 2026, 10:24 p.m.
PD Predicate disambiguation batch_69ccd5acfa5c8190aaba3cf548723604 completed April 1, 2026, 8:22 a.m.
PDg Predicate description generation batch_69ccd93fc45c8190a823305e461e581d completed April 1, 2026, 8:37 a.m.
Created at: March 30, 2026, 8:11 p.m.