Triple

T2967219
Position Surface form Disambiguated ID Type / Status
Subject Istria E80193 entity
Predicate hasLanguage P15 FINISHED
Object Istriot
Istriot is a rare Romance language spoken by a small community in southwestern Istria, notable for its archaic features and uncertain classification within the Romance family.
 E314824 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: Istriot | Statement: [Istria, hasLanguage, Istriot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Istriot
Context triple: [Istria, hasLanguage, Istriot]
  • A. Tosk
    Tosk is the southern variety of Albanian that forms the basis of the standard Albanian language.
  • B. Ibzan
    Ibzan is a minor biblical judge of Israel mentioned in the Book of Judges, known for his large family and brief period of leadership.
  • C. Neša
    Neša is the ancient name of the city of Kültepe, a major Bronze Age trading center and early Hittite capital in central Anatolia.
  • D. Dragovishtitsa
    Dragovishtitsa is a smaller river in western Bulgaria that feeds into the Struma River within the Struma River basin.
  • E. Ginostra
    Ginostra is a tiny, remote village on the southwestern side of the volcanic island of Stromboli in Italy’s Aeolian archipelago, known for its isolation and access only by boat.
  • 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: Istriot
Triple: [Istria, hasLanguage, Istriot]
Generated description
Istriot is a rare Romance language spoken by a small community in southwestern Istria, notable for its archaic features and uncertain classification within the Romance family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Istriot
Target entity description: Istriot is a rare Romance language spoken by a small community in southwestern Istria, notable for its archaic features and uncertain classification within the Romance family.
  • A. Tosk
    Tosk is the southern variety of Albanian that forms the basis of the standard Albanian language.
  • B. Ibzan
    Ibzan is a minor biblical judge of Israel mentioned in the Book of Judges, known for his large family and brief period of leadership.
  • C. Neša
    Neša is the ancient name of the city of Kültepe, a major Bronze Age trading center and early Hittite capital in central Anatolia.
  • D. Dragovishtitsa
    Dragovishtitsa is a smaller river in western Bulgaria that feeds into the Struma River within the Struma River basin.
  • E. Ginostra
    Ginostra is a tiny, remote village on the southwestern side of the volcanic island of Stromboli in Italy’s Aeolian archipelago, known for its isolation and access only by boat.
  • 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_69ad8b14ffe881908ffed62f9595c867 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad996e93788190ba9883714d4dfa0c completed March 8, 2026, 3:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0fc9fcfa48190a5e23ec1f3f01038 completed March 11, 2026, 5:24 a.m.
NEDg Description generation batch_69b100c1bfd48190ab71f460afb096e3 completed March 11, 2026, 5:42 a.m.
NED2 Entity disambiguation (via description) batch_69b10126bd788190b40f3ce1a8a547aa completed March 11, 2026, 5:44 a.m.
Created at: March 8, 2026, 2:58 p.m.