Triple

T10282576
Position Surface form Disambiguated ID Type / Status
Subject Til Schweiger E241140 entity
Predicate name P16 FINISHED
Object Til Schweiger E241140 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: Til Schweiger | Statement: [Til Schweiger, name, Til Schweiger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Til Schweiger
Context triple: [Til Schweiger, name, Til Schweiger]
  • A. Til Schweiger chosen
    Til Schweiger is a prominent German actor, director, and producer known for his roles in both European cinema and Hollywood action films.
  • B. Dieter Fox
    Dieter Fox is a prominent computer scientist and roboticist known for his contributions to probabilistic robotics, perception, and machine learning in autonomous systems.
  • C. Paul Walter Hauser
    Paul Walter Hauser is an American actor and comedian known for his scene-stealing character roles in films and television, including his acclaimed lead performance in "Richard Jewell."
  • D. Christian Kroll
    Christian Kroll is a German entrepreneur best known for creating Ecosia, the eco-friendly search engine that uses its ad revenue to fund tree-planting projects worldwide.
  • E. Hanno Brühl
    Hanno Brühl was a German television director and the father of actor Daniel Brühl.
  • 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_69d381a94c1881908fc38fc263d9b9c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d2a22f9881908b220dbe1e80c101 completed April 7, 2026, 9:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f83c3c488190b728783bc260b006 completed April 9, 2026, 12:52 a.m.
Created at: April 6, 2026, 11:39 a.m.