Triple

T3901361
Position Surface form Disambiguated ID Type / Status
Subject Iserlohn Roosters E90496 entity
Predicate predecessor P97 FINISHED
Object ECD Iserlohn E398238 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: ECD Iserlohn | Statement: [Iserlohn Roosters, predecessor, ECD Iserlohn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ECD Iserlohn
Context triple: [Iserlohn Roosters, predecessor, ECD Iserlohn]
  • A. ECD Iserlohn chosen
    ECD Iserlohn was a German ice hockey club from Iserlohn that served as the predecessor to the modern professional team Iserlohn Roosters.
  • B. Düsseldorfer EG
    Düsseldorfer EG is a professional ice hockey club from Düsseldorf, Germany, known as one of the country’s traditional and historically successful teams.
  • C. Werder (Havel)
    Werder (Havel) is a historic town in Brandenburg, Germany, known for its island old town, fruit-growing traditions, and annual tree blossom festival along the Havel.
  • D. 1. FC Heidenheim
    1. FC Heidenheim is a German professional football club that competes in the Bundesliga and is known for its rapid rise from lower leagues to the top tier.
  • E. VfL Osnabrück
    VfL Osnabrück is a German professional football club based in Osnabrück, Lower Saxony, known for competing primarily in the country’s second and third tiers.
  • 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_69aed95d315881908cbf1bf4a7215fbf completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeecf2f230819099abc109a0b7d916 completed March 9, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5285093208190a2ba00afcbd8a261 completed March 14, 2026, 9:20 a.m.
Created at: March 9, 2026, 3:21 p.m.