Triple

T3088788
Position Surface form Disambiguated ID Type / Status
Subject Olie Kolzig E64438 entity
Predicate familyName P18 FINISHED
Object Kölzig
Kölzig is the surname of former professional ice hockey goaltender Olie Kolzig, best known for his long NHL career with the Washington Capitals.
 E346174 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: Kölzig | Statement: [Olie Kolzig, familyName, Kölzig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kölzig
Context triple: [Olie Kolzig, familyName, Kölzig]
  • A. Kreuth
    Kreuth is a Bavarian municipality in southern Germany, known for its alpine landscape and location near Lake Tegernsee in the Bavarian Alps.
  • B. Kronsberg
    Kronsberg is a location in Germany known, among other things, as the place where former Nazi youth leader Baldur von Schirach died.
  • C. Böbing
    Böbing is a small municipality in the Weilheim-Schongau district of Bavaria, Germany, known for its rural setting in the Alpine foothills.
  • D. Lochau
    Lochau is a locality in Germany historically noted as the place where the influential Reformation-era prince Frederick the Wise died.
  • E. Kelkheim
    Kelkheim is a town in the Main-Taunus district of Hesse, Germany, known for its furniture industry and proximity to Frankfurt.
  • 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: Kölzig
Triple: [Olie Kolzig, familyName, Kölzig]
Generated description
Kölzig is the surname of former professional ice hockey goaltender Olie Kolzig, best known for his long NHL career with the Washington Capitals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kölzig
Target entity description: Kölzig is the surname of former professional ice hockey goaltender Olie Kolzig, best known for his long NHL career with the Washington Capitals.
  • A. Kreuth
    Kreuth is a Bavarian municipality in southern Germany, known for its alpine landscape and location near Lake Tegernsee in the Bavarian Alps.
  • B. Kronsberg
    Kronsberg is a location in Germany known, among other things, as the place where former Nazi youth leader Baldur von Schirach died.
  • C. Böbing
    Böbing is a small municipality in the Weilheim-Schongau district of Bavaria, Germany, known for its rural setting in the Alpine foothills.
  • D. Lochau
    Lochau is a locality in Germany historically noted as the place where the influential Reformation-era prince Frederick the Wise died.
  • E. Kelkheim
    Kelkheim is a town in the Main-Taunus district of Hesse, Germany, known for its furniture industry and proximity to Frankfurt.
  • 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_69ad857c97d88190b26f9b1c90839c77 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada20b99a4819090c3d3e08ed556ad completed March 8, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2f3af69288190869eb648d15ad5e7 completed March 12, 2026, 5:11 p.m.
NEDg Description generation batch_69b2fff1bef8819092db1795240bf9af completed March 12, 2026, 6:03 p.m.
NED2 Entity disambiguation (via description) batch_69b30e8563f481909b64226e133cc744 completed March 12, 2026, 7:05 p.m.
Created at: March 8, 2026, 3:03 p.m.