Triple

T23466822
Position Surface form Disambiguated ID Type / Status
Subject BioProject database E569120 entity
Predicate accessionPrefix P145132 FINISHED
Object PRJEB
PRJEB is an accession prefix used by the BioProject database to identify and group related biological research projects, particularly in European submissions.
E1589490 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: PRJEB | Statement: [BioProject database, accessionPrefix, PRJEB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PRJEB
Context triple: [BioProject database, accessionPrefix, PRJEB]
  • A. Projexx
    Projexx is a Jamaican dancehall and reggae artist known for his melodic style and international collaborations, including work with Nigerian star Wizkid.
  • B. Proj
    Proj is an open-source library for performing cartographic projections and coordinate transformations widely used in geographic information systems.
  • C. Protoje
    Protoje is a Jamaican reggae and dancehall artist known for his role in the modern roots reggae revival and socially conscious lyrics.
  • D. The Project
    The Project is a film featuring actor Michael Stahl-David, best known for his role in the monster movie "Cloverfield."
  • E. The Project
    The Project is an Australian television news and current affairs panel show on Network Ten that blends serious journalism with comedy and pop culture commentary.
  • 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: PRJEB
Triple: [BioProject database, accessionPrefix, PRJEB]
Generated description
PRJEB is an accession prefix used by the BioProject database to identify and group related biological research projects, particularly in European submissions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: PRJEB
Target entity description: PRJEB is an accession prefix used by the BioProject database to identify and group related biological research projects, particularly in European submissions.
  • A. Projexx
    Projexx is a Jamaican dancehall and reggae artist known for his melodic style and international collaborations, including work with Nigerian star Wizkid.
  • B. Proj
    Proj is an open-source library for performing cartographic projections and coordinate transformations widely used in geographic information systems.
  • C. Protoje
    Protoje is a Jamaican reggae and dancehall artist known for his role in the modern roots reggae revival and socially conscious lyrics.
  • D. The Project
    The Project is a film featuring actor Michael Stahl-David, best known for his role in the monster movie "Cloverfield."
  • E. The Project
    The Project is an Australian television news and current affairs panel show on Network Ten that blends serious journalism with comedy and pop culture commentary.
  • 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_69e2458ebd808190b3298163132cfb0b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a6fc35c48190a67614fb4170f15b completed April 29, 2026, 6:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c8254f3fc819098b6b59eb19e27f0 completed May 19, 2026, 3:31 p.m.
NEDg Description generation batch_6a0ca6efb0d88190bf15b18cc3f12482 completed May 19, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0ca80db6288190ae99313c1f2485db completed May 19, 2026, 6:12 p.m.
Created at: April 17, 2026, 5:54 p.m.