Triple

T13331127
Position Surface form Disambiguated ID Type / Status
Subject Daniel Wu E317573 entity
Predicate notableWork P4 FINISHED
Object Overheard
Overheard is a Hong Kong crime thriller film featuring Daniel Wu in a story centered on high-stakes surveillance and financial intrigue.
E1035960 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: Overheard | Statement: [Daniel Wu, notableWork, Overheard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Overheard
Context triple: [Daniel Wu, notableWork, Overheard]
  • A. Heard 'Em Say
    "Heard 'Em Say" is a reflective, soulful hip-hop song by Kanye West featuring Adam Levine, known for its introspective lyrics and mellow production.
  • B. Things Heard & Seen
    Things Heard & Seen is a 2021 supernatural horror drama film that blends marital thriller elements with ghost story themes, based on the novel "All Things Cease to Appear" by Elizabeth Brundage.
  • C. Oh, No, You Didn’t
    "Oh, No, You Didn’t" is a song featured on the country music album "Halfway to Home" by American singer-songwriter Brandy Clark.
  • D. Showing Out
    "Showing Out" is a track by hip-hop duo Clipse from their 2009 studio album "Til the Casket Drops."
  • E. Last Seen Wearing
    "Last Seen Wearing" is a crime novel in Colin Dexter's Inspector Morse series, featuring the detective's investigation into the disappearance of a schoolgirl.
  • 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: Overheard
Triple: [Daniel Wu, notableWork, Overheard]
Generated description
Overheard is a Hong Kong crime thriller film featuring Daniel Wu in a story centered on high-stakes surveillance and financial intrigue.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Overheard
Target entity description: Overheard is a Hong Kong crime thriller film featuring Daniel Wu in a story centered on high-stakes surveillance and financial intrigue.
  • A. Heard 'Em Say
    "Heard 'Em Say" is a reflective, soulful hip-hop song by Kanye West featuring Adam Levine, known for its introspective lyrics and mellow production.
  • B. Things Heard & Seen
    Things Heard & Seen is a 2021 supernatural horror drama film that blends marital thriller elements with ghost story themes, based on the novel "All Things Cease to Appear" by Elizabeth Brundage.
  • C. Oh, No, You Didn’t
    "Oh, No, You Didn’t" is a song featured on the country music album "Halfway to Home" by American singer-songwriter Brandy Clark.
  • D. Showing Out
    "Showing Out" is a track by hip-hop duo Clipse from their 2009 studio album "Til the Casket Drops."
  • E. Last Seen Wearing
    "Last Seen Wearing" is a crime novel in Colin Dexter's Inspector Morse series, featuring the detective's investigation into the disappearance of a schoolgirl.
  • 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_69d806b4d62c81908d4ced1665414be5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9992fffa0819086610ae3bed2e2f9 completed April 11, 2026, 12:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69f71f329e148190a7741344b27ea663 completed May 3, 2026, 10:10 a.m.
NEDg Description generation batch_69f7231e7f5881908dde74ad279362ed completed May 3, 2026, 10:27 a.m.
NED2 Entity disambiguation (via description) batch_69f723a23524819082c15e048ebff350 completed May 3, 2026, 10:29 a.m.
Created at: April 9, 2026, 9:30 p.m.