Triple

T1787852
Position Surface form Disambiguated ID Type / Status
Subject Ava DuVernay E39428 entity
Predicate founded P104 FINISHED
Object ARRAY
ARRAY is a film distribution and resource collective dedicated to amplifying the work of women and people of color in the independent film industry.
 E199115 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: ARRAY | Statement: [Ava DuVernay, founded, ARRAY]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ARRAY
Context triple: [Ava DuVernay, founded, ARRAY]
  • A. Matrix
    Matrix is a professional haircare and hair color brand widely used in salons and owned by the cosmetics company L'Oréal.
  • B. Matrix
    The Matrix is a vast, sentient data repository and virtual reality construct on Gallifrey that stores the knowledge, memories, and consciousness of Time Lords in the Doctor Who universe.
  • C. AR
    AR is the standard abbreviation for the Romanian Academy, the leading national institution for the promotion of science, culture, and the arts in Romania.
  • D. AR
    AR is the commonly used abbreviation for the Assembly of the Republic, the unicameral national parliament of Portugal.
  • E. AR
    AR is the official two-letter United States Postal Service abbreviation for the state of Arkansas.
  • 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: ARRAY
Triple: [Ava DuVernay, founded, ARRAY]
Generated description
ARRAY is a film distribution and resource collective dedicated to amplifying the work of women and people of color in the independent film industry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ARRAY
Target entity description: ARRAY is a film distribution and resource collective dedicated to amplifying the work of women and people of color in the independent film industry.
  • A. Matrix
    Matrix is a professional haircare and hair color brand widely used in salons and owned by the cosmetics company L'Oréal.
  • B. Matrix
    The Matrix is a vast, sentient data repository and virtual reality construct on Gallifrey that stores the knowledge, memories, and consciousness of Time Lords in the Doctor Who universe.
  • C. AR
    AR is the commonly used abbreviation for the Assembly of the Republic, the unicameral national parliament of Portugal.
  • D. AR
    AR is the standard abbreviation for the Romanian Academy, the leading national institution for the promotion of science, culture, and the arts in Romania.
  • E. AR
    AR is the two-letter IATA airline designator assigned to Aerolíneas Argentinas, the flag carrier of Argentina.
  • 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_69a88631854081909723959921e45c2b completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa650fd3448190a6a2c979db982cae completed March 6, 2026, 5:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada9a8a69c8190885bf06a06d3869f completed March 8, 2026, 4:54 p.m.
NEDg Description generation batch_69adaab488ec81909a340aab4916b90f completed March 8, 2026, 4:58 p.m.
NED2 Entity disambiguation (via description) batch_69adaf3cd23081909dd27c5de8e3f6d2 completed March 8, 2026, 5:17 p.m.
Created at: March 4, 2026, 7:32 p.m.