Triple

T22573744
Position Surface form Disambiguated ID Type / Status
Subject Kissing on the Mouth E544338 entity
Predicate productionCompany P490 FINISHED
Object Hi-Def Film
Hi-Def Film is a film production company known for its work on independent features such as the drama "Kissing on the Mouth."
 E1543040 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: Hi-Def Film | Statement: [Kissing on the Mouth, productionCompany, Hi-Def Film]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hi-Def Film
Context triple: [Kissing on the Mouth, productionCompany, Hi-Def Film]
  • A. HDTV
    HDTV (High-Definition Television) is a television broadcasting standard that delivers significantly higher resolution, improved picture clarity, and better color quality compared to traditional standard-definition TV.
  • B. HD
    HD is the New York Stock Exchange ticker symbol for The Home Depot, the largest home improvement retail chain in the United States.
  • C. HD
    HD is the standard astronomical abbreviation for the Henry Draper Catalogue, a widely used star catalog that assigns spectral classifications and identifiers to hundreds of thousands of stars.
  • D. HD
    HD is the vehicle registration code used for the German city of Heidelberg.
  • E. HD
    HD is a postcode area in the United Kingdom covering Huddersfield and its surrounding districts in West Yorkshire.
  • 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: Hi-Def Film
Triple: [Kissing on the Mouth, productionCompany, Hi-Def Film]
Generated description
Hi-Def Film is a film production company known for its work on independent features such as the drama "Kissing on the Mouth."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hi-Def Film
Target entity description: Hi-Def Film is a film production company known for its work on independent features such as the drama "Kissing on the Mouth."
  • A. HDTV
    HDTV (High-Definition Television) is a television broadcasting standard that delivers significantly higher resolution, improved picture clarity, and better color quality compared to traditional standard-definition TV.
  • B. HD
    HD is the New York Stock Exchange ticker symbol for The Home Depot, the largest home improvement retail chain in the United States.
  • C. HD
    HD is the vehicle registration code used for the German city of Heidelberg.
  • D. HD
    HD is the standard astronomical abbreviation for the Henry Draper Catalogue, a widely used star catalog that assigns spectral classifications and identifiers to hundreds of thousands of stars.
  • E. HD
    HD is a postcode area in the United Kingdom covering Huddersfield and its surrounding districts in West Yorkshire.
  • 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_69e11e30d05481909df915354c89f0d6 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f15fea683c81908fbf9f171eed3341 completed April 29, 2026, 1:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b2d7ad7888190b2815c074475d932 completed May 18, 2026, 3:17 p.m.
NEDg Description generation batch_6a0b3648cb208190b749e343c3d5c88d completed May 18, 2026, 3:54 p.m.
NED2 Entity disambiguation (via description) batch_6a0b37002120819097bf1f6e56b6afe5 completed May 18, 2026, 3:57 p.m.
Created at: April 16, 2026, 8:53 p.m.