Triple

T20999805
Position Surface form Disambiguated ID Type / Status
Subject Sukoharjo Regency E517254 entity
Predicate hasVehicleRegistrationCode P1173 FINISHED
Object AD
AD is an Indonesian vehicle registration code used for motor vehicles registered in parts of Central Java, including Sukoharjo Regency.
 E1461963 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: AD | Statement: [Sukoharjo Regency, hasVehicleRegistrationCode, AD]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AD
Context triple: [Sukoharjo Regency, hasVehicleRegistrationCode, AD]
  • A. AD
    AD is a CERN facility that slows down antiprotons so they can be used in precision experiments studying antimatter.
  • B. AD
    AD is the two-letter country code for Andorra, a small landlocked principality in the Pyrenees between France and Spain.
  • C. AD
    AD is the commonly used abbreviation for the French political party Democratic Republican Alliance, a centrist-liberal force active during the Third Republic.
  • D. AD
    AD is the widely used nickname for Anthony Davis, an American professional basketball star known for his elite shot-blocking, rebounding, and scoring ability in the NBA.
  • E. AD
    AD is the commonly used abbreviation for Acción Democrática, a major social-democratic political party in Venezuela.
  • 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: AD
Triple: [Sukoharjo Regency, hasVehicleRegistrationCode, AD]
Generated description
AD is an Indonesian vehicle registration code used for motor vehicles registered in parts of Central Java, including Sukoharjo Regency.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AD
Target entity description: AD is an Indonesian vehicle registration code used for motor vehicles registered in parts of Central Java, including Sukoharjo Regency.
  • A. AD
    AD is a CERN facility that slows down antiprotons so they can be used in precision experiments studying antimatter.
  • B. AD
    AD is the commonly used abbreviation for the French political party Democratic Republican Alliance, a centrist-liberal force active during the Third Republic.
  • C. AD
    AD is the widely used nickname for Anthony Davis, an American professional basketball star known for his elite shot-blocking, rebounding, and scoring ability in the NBA.
  • D. AD
    AD is the commonly used abbreviation for Acción Democrática, a major social-democratic political party in Venezuela.
  • E. AD
    AD is the two-letter country code for Andorra, a small landlocked principality in the Pyrenees between France and Spain.
  • 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_69e0b5006e2881909fc2383f841740cc completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc24a6dc8190a6bf81cf1d9590c0 completed April 21, 2026, 4:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a093b545f5081909152211b7e03bea1 completed May 17, 2026, 3:51 a.m.
NEDg Description generation batch_6a093e5b743881908dea54f627f2a220 completed May 17, 2026, 4:04 a.m.
NED2 Entity disambiguation (via description) batch_6a093ebe37cc8190961b02f8f12ce4b0 completed May 17, 2026, 4:06 a.m.
Created at: April 16, 2026, 1:51 p.m.