Triple

T18406274
Position Surface form Disambiguated ID Type / Status
Subject Duklja E450132 entity
Predicate capital P234 FINISHED
Object Doclea
Doclea was an ancient city in present-day Montenegro that served as a key political and administrative center in the early medieval Balkans.
E1322324 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: Doclea | Statement: [Duklja, capital, Doclea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Doclea
Context triple: [Duklja, capital, Doclea]
  • A. Huridocs
    Huridocs is an international NGO that develops tools and strategies to help human rights organizations manage, analyze, and use information effectively.
  • B. Docus
    Docus is an alternative name for Dok, likely referring to the same entity, brand, or product under a different designation.
  • C. Zoho Docs
    Zoho Docs is a cloud-based document management and collaboration platform that allows users to create, store, share, and manage files online as part of the Zoho productivity suite.
  • D. DOCU
    DOCU is the stock ticker symbol for DocuSign, a leading provider of electronic signature and digital agreement management solutions.
  • 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: Doclea
Triple: [Duklja, capital, Doclea]
Generated description
Doclea was an ancient city in present-day Montenegro that served as a key political and administrative center in the early medieval Balkans.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Doclea
Target entity description: Doclea was an ancient city in present-day Montenegro that served as a key political and administrative center in the early medieval Balkans.
  • A. Huridocs
    Huridocs is an international NGO that develops tools and strategies to help human rights organizations manage, analyze, and use information effectively.
  • B. Docus
    Docus is an alternative name for Dok, likely referring to the same entity, brand, or product under a different designation.
  • C. Zoho Docs
    Zoho Docs is a cloud-based document management and collaboration platform that allows users to create, store, share, and manage files online as part of the Zoho productivity suite.
  • D. DOCU
    DOCU is the stock ticker symbol for DocuSign, a leading provider of electronic signature and digital agreement management solutions.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e51957ac7081909a2dd2b2308e4170 completed April 19, 2026, 6:05 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03e2480ec881909d92a2303fc8409f completed May 13, 2026, 2:30 a.m.
NEDg Description generation batch_6a03e341afa881909fce49af047d0a83 completed May 13, 2026, 2:34 a.m.
NED2 Entity disambiguation (via description) batch_6a03e3ac2f4081908e086f8efd1393ae completed May 13, 2026, 2:36 a.m.
Created at: April 10, 2026, 10:46 a.m.