Triple

T17973556
Position Surface form Disambiguated ID Type / Status
Subject Two-Face E449405 entity
Predicate notableStoryline P7331 FINISHED
Object Hush
Hush is a major Batman comic book storyline that introduces the bandage-faced villain Hush and follows a complex conspiracy involving many of Gotham City’s key characters.
 E1303431 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: Hush | Statement: [Two-Face, notableStoryline, Hush]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hush
Context triple: [Two-Face, notableStoryline, Hush]
  • A. Hush
    "Hush" is a critically acclaimed, largely dialogue-free horror episode of *Buffy the Vampire Slayer* renowned for its eerie villains, The Gentlemen, and its inventive use of silence.
  • B. Hush
    Hush is a 2016 horror-thriller film directed and co-written by Mike Flanagan, centered on a deaf-mute woman fighting for survival against a masked killer at her isolated home.
  • C. Hush
    "Hush" is a 1967 rock song written by Joe South, best known for becoming a hit through Deep Purple’s 1968 cover version.
  • D. Hush
    Hush is a song famously performed by American singer Dolores Hope, showcasing her smooth vocal style in traditional pop music.
  • E. Whisper
    Whisper is an open-source automatic speech recognition system by OpenAI that transcribes and translates spoken language with high accuracy across many languages.
  • 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: Hush
Triple: [Two-Face, notableStoryline, Hush]
Generated description
Hush is a major Batman comic book storyline that introduces the bandage-faced villain Hush and follows a complex conspiracy involving many of Gotham City’s key characters.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hush
Target entity description: Hush is a major Batman comic book storyline that introduces the bandage-faced villain Hush and follows a complex conspiracy involving many of Gotham City’s key characters.
  • A. Hush
    "Hush" is a critically acclaimed, largely dialogue-free horror episode of *Buffy the Vampire Slayer* renowned for its eerie villains, The Gentlemen, and its inventive use of silence.
  • B. Hush
    Hush is a 2016 horror-thriller film directed and co-written by Mike Flanagan, centered on a deaf-mute woman fighting for survival against a masked killer at her isolated home.
  • C. Hush
    "Hush" is a 1967 rock song written by Joe South, best known for becoming a hit through Deep Purple’s 1968 cover version.
  • D. Hush
    Hush is a song famously performed by American singer Dolores Hope, showcasing her smooth vocal style in traditional pop music.
  • E. Whisper
    Whisper is an open-source automatic speech recognition system by OpenAI that transcribes and translates spoken language with high accuracy across many languages.
  • 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_69d8b9f9927c8190a006110c8b996e61 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b1fca04481908f0dd875953fd82f completed April 19, 2026, 10:44 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0349a29b9881909105d604922addc1 completed May 12, 2026, 3:39 p.m.
NEDg Description generation batch_6a03534989c48190983c69560fdad0f9 completed May 12, 2026, 4:20 p.m.
NED2 Entity disambiguation (via description) batch_6a0353bded048190b32a116aa89ce3b0 completed May 12, 2026, 4:22 p.m.
Created at: April 10, 2026, 10:22 a.m.