Triple

T10790942
Position Surface form Disambiguated ID Type / Status
Subject Jacques Demy E254574 entity
Predicate notableWork P4 FINISHED
Object Parking
Parking is a 1985 French musical fantasy film by Jacques Demy that reimagines the Orpheus myth in a contemporary setting.
E886059 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: Parking | Statement: [Jacques Demy, notableWork, Parking]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parking
Context triple: [Jacques Demy, notableWork, Parking]
  • A. Popular End parking
    Popular End parking is a car park commonly used by visitors accessing the Popular End climbing and walking areas of Stanage Edge in the Peak District.
  • B. Parkar
    Parkar is a less common spelling variant of the surname Parker, which is of English origin.
  • C. Parkend
    Parkend is a small village situated within England’s historic Forest of Dean, known for its woodland surroundings and industrial heritage.
  • D. Parkring
    Parkring is a central boulevard in Vienna that forms part of the historic Ringstrasse, known for its grand architecture and proximity to prominent parks and landmarks.
  • E. The Parking Garage
    "The Parking Garage" is a famous Seinfeld episode in which the four main characters wander a multi-level parking structure, unable to find their car, turning a mundane situation into escalating absurdity.
  • 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: Parking
Triple: [Jacques Demy, notableWork, Parking]
Generated description
Parking is a 1985 French musical fantasy film by Jacques Demy that reimagines the Orpheus myth in a contemporary setting.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Parking
Target entity description: Parking is a 1985 French musical fantasy film by Jacques Demy that reimagines the Orpheus myth in a contemporary setting.
  • A. Popular End parking
    Popular End parking is a car park commonly used by visitors accessing the Popular End climbing and walking areas of Stanage Edge in the Peak District.
  • B. Parkar
    Parkar is a less common spelling variant of the surname Parker, which is of English origin.
  • C. Parkend
    Parkend is a small village situated within England’s historic Forest of Dean, known for its woodland surroundings and industrial heritage.
  • D. Parkring
    Parkring is a central boulevard in Vienna that forms part of the historic Ringstrasse, known for its grand architecture and proximity to prominent parks and landmarks.
  • E. The Parking Garage
    "The Parking Garage" is a famous Seinfeld episode in which the four main characters wander a multi-level parking structure, unable to find their car, turning a mundane situation into escalating absurdity.
  • 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_69d6aa609f008190a294200aefcb7bd5 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d732f5b8248190a633dc44ae620a3a completed April 9, 2026, 5:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69de5637ec50819087f1a0372f89197d completed April 14, 2026, 2:59 p.m.
NEDg Description generation batch_69de5eadb9448190bdf69711394e2ab7 completed April 14, 2026, 3:35 p.m.
NED2 Entity disambiguation (via description) batch_69de607917808190922df6521d7bfb07 completed April 14, 2026, 3:42 p.m.
Created at: April 8, 2026, 9:17 p.m.