Triple

T18710501
Position Surface form Disambiguated ID Type / Status
Subject Maxime Alexandre E457494 entity
Predicate workedOn P3 FINISHED
Object P2 (film)
P2 is a 2007 horror-thriller film set in a parking garage on Christmas Eve, in which a businesswoman is terrorized by a deranged security guard.
 E1338812 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: P2 (film) | Statement: [Maxime Alexandre, workedOn, P2 (film)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: P2 (film)
Context triple: [Maxime Alexandre, workedOn, P2 (film)]
  • A. La Pandorga
    La Pandorga is a traditional summer festival in Ciudad Real, Spain, featuring religious offerings, folk music, dancing, and local cultural celebrations.
  • B. Pariah
    Pariah is a 2011 independent coming-of-age drama film about a Brooklyn teenager embracing her identity as a lesbian, noted for its intimate storytelling and evocative cinematography.
  • C. Pariah
    Pariah is a film production company known for producing the post-apocalyptic zombie comedy "Zombieland."
  • D. Paasaal
    Paasaal is a dialect of the Sisaala language spoken by communities in northern Ghana and neighboring areas of West Africa.
  • E. Pami Dua
    Pami Dua is an Indian economist and academic known for her contributions to econometrics and macroeconomic policy research, and for her leadership roles at the Delhi School of Economics.
  • 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: P2 (film)
Triple: [Maxime Alexandre, workedOn, P2 (film)]
Generated description
P2 is a 2007 horror-thriller film set in a parking garage on Christmas Eve, in which a businesswoman is terrorized by a deranged security guard.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: P2 (film)
Target entity description: P2 is a 2007 horror-thriller film set in a parking garage on Christmas Eve, in which a businesswoman is terrorized by a deranged security guard.
  • A. La Pandorga
    La Pandorga is a traditional summer festival in Ciudad Real, Spain, featuring religious offerings, folk music, dancing, and local cultural celebrations.
  • B. Pariah
    Pariah is a 2011 independent coming-of-age drama film about a Brooklyn teenager embracing her identity as a lesbian, noted for its intimate storytelling and evocative cinematography.
  • C. Pariah
    Pariah is a film production company known for producing the post-apocalyptic zombie comedy "Zombieland."
  • D. Paasaal
    Paasaal is a dialect of the Sisaala language spoken by communities in northern Ghana and neighboring areas of West Africa.
  • E. Pami Dua
    Pami Dua is an Indian economist and academic known for her contributions to econometrics and macroeconomic policy research, and for her leadership roles at the Delhi School of Economics.
  • 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5671b34508190b6180f7d6ad50a58 completed April 19, 2026, 11:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a052b3f247c8190922c4ce9f67301a0 completed May 14, 2026, 1:54 a.m.
NEDg Description generation batch_6a052c6373088190a81e53963dac9c6f completed May 14, 2026, 1:58 a.m.
NED2 Entity disambiguation (via description) batch_6a052d6f1f8081908810e99dff28b586 completed May 14, 2026, 2:03 a.m.
Created at: April 10, 2026, 11:50 a.m.