Triple

T19754651
Position Surface form Disambiguated ID Type / Status
Subject Un Lun Dun E474471 entity
Predicate antagonist P4675 FINISHED
Object Smog
Smog is a sentient, malevolent cloud of pollution that serves as the primary villain in China Miéville’s fantasy novel "Un Lun Dun."
E1393741 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: Smog | Statement: [Un Lun Dun, antagonist, Smog]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Smog
Context triple: [Un Lun Dun, antagonist, Smog]
  • A. Smog
    Smog is the lo-fi indie rock project of American singer-songwriter Bill Callahan, known for its sparse arrangements and introspective, deadpan lyricism.
  • B. Haze
    Haze is the surname of Dolores "Lolita" Haze, the fictional adolescent protagonist of Vladimir Nabokov’s novel "Lolita."
  • C. Fog
    "Fog" is a brief, imagistic poem by Carl Sandburg that famously compares fog to a silent cat, exemplifying his modern, accessible style.
  • D. The Smoke
    The Smoke is the English name of Surah Ad-Dukhan, a chapter of the Qur’an that warns of a coming smoke as a sign of divine punishment and emphasizes God’s power and mercy.
  • E. The Smoke
    The Smoke is a British television drama series centered on the lives and challenges of London firefighters.
  • 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: Smog
Triple: [Un Lun Dun, antagonist, Smog]
Generated description
Smog is a sentient, malevolent cloud of pollution that serves as the primary villain in China Miéville’s fantasy novel "Un Lun Dun."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Smog
Target entity description: Smog is a sentient, malevolent cloud of pollution that serves as the primary villain in China Miéville’s fantasy novel "Un Lun Dun."
  • A. Smog
    Smog is the lo-fi indie rock project of American singer-songwriter Bill Callahan, known for its sparse arrangements and introspective, deadpan lyricism.
  • B. Haze
    Haze is the surname of Dolores "Lolita" Haze, the fictional adolescent protagonist of Vladimir Nabokov’s novel "Lolita."
  • C. Fog
    "Fog" is a brief, imagistic poem by Carl Sandburg that famously compares fog to a silent cat, exemplifying his modern, accessible style.
  • D. The Smoke
    The Smoke is a dramatic work by British playwright Lucy Kirkwood, known for her sharp, socially engaged storytelling.
  • E. The Smoke
    The Smoke is the English name of Surah Ad-Dukhan, a chapter of the Qur’an that warns of a coming smoke as a sign of divine punishment and emphasizes God’s power and mercy.
  • 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529dada081909c5b4d65247c6032 completed April 20, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07bd67064081908839a408b0e746e1 completed May 16, 2026, 12:42 a.m.
NEDg Description generation batch_6a07bde28e848190aaa9c4a06b31bdb6 completed May 16, 2026, 12:44 a.m.
NED2 Entity disambiguation (via description) batch_6a07bed9c62c819088d8e32f92b3b147 completed May 16, 2026, 12:48 a.m.
Created at: April 10, 2026, 1:48 p.m.