Triple

T23006293
Position Surface form Disambiguated ID Type / Status
Subject Udo Kier E572778 entity
Predicate notableWork P4 FINISHED
Object Swan Song
Swan Song is a 2021 drama film in which Udo Kier stars as a retired, flamboyant hairdresser who embarks on a bittersweet journey to style a former client’s hair one last time.
E1565011 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: Swan Song | Statement: [Udo Kier, notableWork, Swan Song]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swan Song
Context triple: [Udo Kier, notableWork, Swan Song]
  • A. Swan Song
    Swan Song is a 2021 science fiction drama film starring Mahershala Ali as a terminally ill man who considers cloning himself to spare his family grief.
  • B. Swan Song
    Swan Song is the English title commonly used for Franz Schubert’s posthumously published collection of late lieder known as "Schwanengesang."
  • C. Swan Song
    "Swan Song" is a bonus track by Lana Del Rey, known for its cinematic, melancholic style and themes of escape and finality.
  • D. Swan Song
    "Swan Song" is a segment or episode within the 1924 silent film anthology *A Modern Comedy*, likely serving as one of its narrative parts.
  • E. Swan Song
    Swan Song is the final novel in John Galsworthy’s Forsyte Saga, concluding the multigenerational story of the Forsyte family.
  • 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: Swan Song
Triple: [Udo Kier, notableWork, Swan Song]
Generated description
Swan Song is a 2021 drama film in which Udo Kier stars as a retired, flamboyant hairdresser who embarks on a bittersweet journey to style a former client’s hair one last time.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Swan Song
Target entity description: Swan Song is a 2021 drama film in which Udo Kier stars as a retired, flamboyant hairdresser who embarks on a bittersweet journey to style a former client’s hair one last time.
  • A. Swan Song
    Swan Song is a 2021 science fiction drama film starring Mahershala Ali as a terminally ill man who considers cloning himself to spare his family grief.
  • B. Swan Song
    "Swan Song" is a bonus track by Lana Del Rey, known for its cinematic, melancholic style and themes of escape and finality.
  • C. Swan Song
    Swan Song is the final novel in John Galsworthy’s Forsyte Saga, concluding the multigenerational story of the Forsyte family.
  • D. Swan Song
    "Swan Song" is a segment or episode within the 1924 silent film anthology *A Modern Comedy*, likely serving as one of its narrative parts.
  • E. Swan Song
    "Swan Song" is a track by Bruce Hornsby known for its reflective lyrics and melodic piano-driven arrangement.
  • 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_69e245b6a3ac81908087599eefe3e365 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1835706dc8190b3f9743c0f336bb2 completed April 29, 2026, 4:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bd3846500819094a1bb01797d22a5 completed May 19, 2026, 3:05 a.m.
NEDg Description generation batch_6a0bd41c89708190a3df2a798ca25c99 completed May 19, 2026, 3:08 a.m.
NED2 Entity disambiguation (via description) batch_6a0bd5263734819082ce8b1c3082243f completed May 19, 2026, 3:12 a.m.
Created at: April 17, 2026, 3:51 p.m.