Triple

T6456360
Position Surface form Disambiguated ID Type / Status
Subject MIPTV E142001 entity
Predicate relatedEvent P37 FINISHED
Object MIPDoc
MIPDoc is an international documentary and factual content market and conference that runs alongside MIPTV, bringing together producers, buyers, and distributors from the global non-fiction industry.
 E593505 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: MIPDoc | Statement: [MIPTV, relatedEvent, MIPDoc]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MIPDoc
Context triple: [MIPTV, relatedEvent, MIPDoc]
  • A. MIP
    MIP is a U.S. Department of Defense funding and oversight framework that supports military intelligence activities, systems, and operations.
  • B. MADOC
    MADOC is the state agency responsible for overseeing and managing the prison and correctional system in Massachusetts.
  • C. .md
    .md is the country code top-level domain (ccTLD) assigned to Moldova, also popularly used by medical professionals and sites related to medicine due to the "MD" abbreviation.
  • D. DOCO
    DOCO is a mixed-use entertainment, shopping, and dining district in downtown Sacramento, California, adjacent to the Golden 1 Center.
  • E. docuverse
    Docuverse is Ted Nelson’s visionary concept of a universal, interconnected digital library where all documents are permanently linked and traceable across a global hypertext system.
  • 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: MIPDoc
Triple: [MIPTV, relatedEvent, MIPDoc]
Generated description
MIPDoc is an international documentary and factual content market and conference that runs alongside MIPTV, bringing together producers, buyers, and distributors from the global non-fiction industry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MIPDoc
Target entity description: MIPDoc is an international documentary and factual content market and conference that runs alongside MIPTV, bringing together producers, buyers, and distributors from the global non-fiction industry.
  • A. MIP
    MIP is a U.S. Department of Defense funding and oversight framework that supports military intelligence activities, systems, and operations.
  • B. MADOC
    MADOC is the state agency responsible for overseeing and managing the prison and correctional system in Massachusetts.
  • C. .md
    .md is the country code top-level domain (ccTLD) assigned to Moldova, also popularly used by medical professionals and sites related to medicine due to the "MD" abbreviation.
  • D. DOCO
    DOCO is a mixed-use entertainment, shopping, and dining district in downtown Sacramento, California, adjacent to the Golden 1 Center.
  • E. docuverse
    Docuverse is Ted Nelson’s visionary concept of a universal, interconnected digital library where all documents are permanently linked and traceable across a global hypertext system.
  • 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_69c008d2f91c8190a8178767a35e08fc completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c069d639ec8190bb0a806da4118440 completed March 22, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69c64bdc4e808190a7c24b963ab0aa30 completed March 27, 2026, 9:20 a.m.
NEDg Description generation batch_69c64ce18f6c8190910dcc2fc553328e completed March 27, 2026, 9:24 a.m.
NED2 Entity disambiguation (via description) batch_69c64db784f08190b786c4de051ee527 completed March 27, 2026, 9:28 a.m.
Created at: March 22, 2026, 4:48 p.m.