Triple

T16984915
Position Surface form Disambiguated ID Type / Status
Subject University of Picardy Jules Verne E412038 entity
Predicate shortName P43 FINISHED
Object UPJV
UPJV is the commonly used acronym for the University of Picardy Jules Verne, a French public university based in Amiens.
E1243985 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: UPJV | Statement: [University of Picardy Jules Verne, shortName, UPJV]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UPJV
Context triple: [University of Picardy Jules Verne, shortName, UPJV]
  • A. TUPJ
    TUPJ is the ICAO airport code for Terrance B. Lettsome International Airport, the main air gateway to the British Virgin Islands.
  • B. UPV
    UPV is the commonly used acronym for the Polytechnic University of Valencia, a major Spanish public technical university known for its engineering and technology programs.
  • C. PUJ
    PUJ is the IATA airport code for Punta Cana International Airport, a major tourist gateway in the Dominican Republic.
  • D. IPU
    IPU (Intelligence Processing Unit) is Graphcore's specialized processor architecture designed to accelerate machine learning and artificial intelligence workloads.
  • E. IPU
    IPU is the commonly used abbreviation for the Inter-Parliamentary Union, a global organization that fosters cooperation and dialogue among national parliaments.
  • 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: UPJV
Triple: [University of Picardy Jules Verne, shortName, UPJV]
Generated description
UPJV is the commonly used acronym for the University of Picardy Jules Verne, a French public university based in Amiens.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: UPJV
Target entity description: UPJV is the commonly used acronym for the University of Picardy Jules Verne, a French public university based in Amiens.
  • A. TUPJ
    TUPJ is the ICAO airport code for Terrance B. Lettsome International Airport, the main air gateway to the British Virgin Islands.
  • B. UPV
    UPV is the commonly used acronym for the Polytechnic University of Valencia, a major Spanish public technical university known for its engineering and technology programs.
  • C. PUJ
    PUJ is the IATA airport code for Punta Cana International Airport, a major tourist gateway in the Dominican Republic.
  • D. IPU
    IPU (Intelligence Processing Unit) is Graphcore's specialized processor architecture designed to accelerate machine learning and artificial intelligence workloads.
  • E. IPU
    IPU is the commonly used abbreviation for the Inter-Parliamentary Union, a global organization that fosters cooperation and dialogue among national parliaments.
  • 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_69d886ca8f348190812768ea8d5055ce completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d18af95c8190a25ef0614e1a17f3 completed April 18, 2026, 6:46 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00dc0f13c88190b55da5be40a0a476 completed May 10, 2026, 7:27 p.m.
NEDg Description generation batch_6a00dc96a9588190b020fd7fd1deee2b completed May 10, 2026, 7:29 p.m.
NED2 Entity disambiguation (via description) batch_6a0114e04e00819093805024f8417fad completed May 10, 2026, 11:29 p.m.
Created at: April 10, 2026, 5:32 a.m.