Triple

T8109618
Position Surface form Disambiguated ID Type / Status
Subject PH E189314 entity
Predicate registrationArea P48529 FINISHED
Object Ploiești E277709 NE FINISHED

How this triple was built (3 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: Ploiești | Statement: [PH, registrationArea, Ploiești]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ploiești
Context triple: [PH, registrationArea, Ploiești]
  • A. Ploiești chosen
    Ploiești is a major city in southern Romania historically known for its oil industry and strategic importance during World War II.
  • B. Pitești
    Pitești is a city in southern Romania, known as an important industrial and transportation hub and the capital of Argeș County.
  • C. Craiova
    Craiova is a major city in southwestern Romania, known as an important economic, cultural, and university center of the historical region of Oltenia.
  • D. Miercurea Ciuc
    Miercurea Ciuc is a town in eastern Transylvania, Romania, known as a cultural center of the Székely Hungarian community and for its cold climate.
  • E. Brașov
    Brașov is a historic city in central Romania, renowned for its well-preserved medieval architecture, fortified churches, and role as a major cultural and economic center of Transylvania.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: registrationArea
Context triple: [PH, registrationArea, Ploiești]
  • A. inscriptionLocation
    Indicates the place or surface on which an inscription is written or engraved.
  • B. registrationCategory
    Indicates the classification or type under which an entity is formally registered within a system or registry.
  • C. regulatedArea
    Indicates that an area is subject to specific rules, controls, or restrictions imposed by an authority.
  • D. registrationSystem
    Indicates a system or process responsible for recording, managing, and maintaining registrations or enrollments for entities.
  • E. reportingArea chosen
    Indicates that one entity serves as the geographic or organizational area for which information, data, or events about another entity are reported or aggregated.
  • F. None of above.

Provenance (4 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_69ca82b9d5848190a24672775d5c5011 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4664fef881908b0dc7b158aca398 completed March 31, 2026, 3:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfaae99194819095cf9b74267956a4 completed April 3, 2026, 11:56 a.m.
PD Predicate disambiguation batch_69cb368e7f4c81909aabd7716f0de79d completed March 31, 2026, 2:50 a.m.
Created at: March 30, 2026, 5:32 p.m.