Triple

T12835223
Position Surface form Disambiguated ID Type / Status
Subject Odukpani E306891 entity
Predicate hasISO3166-2Code P208 FINISHED
Object NG-CR
NG-CR is the ISO 3166-2 subdivision code assigned to Cross River State in Nigeria.
 E1005106 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: NG-CR | Statement: [Odukpani, hasISO3166-2Code, NG-CR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: NG-CR
Context triple: [Odukpani, hasISO3166-2Code, NG-CR]
  • A. crg
    crg is the ISO 639-3 language code for Michif, the mixed Cree–French language traditionally spoken by Métis communities in Canada and parts of the United States.
  • B. CR 527
    CR 527 is a county highway in New Jersey that runs through multiple counties, serving as a significant north–south arterial route.
  • C. NKG
    NKG is the IATA airport code for Nanjing Lukou International Airport, the main commercial airport serving Nanjing in eastern China.
  • D. CRCL
    CRCL is the Office for Civil Rights and Civil Liberties within the U.S. Department of Homeland Security, responsible for ensuring that civil rights and civil liberties are protected in the department’s policies and activities.
  • E. CRD
    CRD is a centralized online database maintained by FINRA that contains licensing and registration information on broker-dealers and their associated individuals in the U.S. financial industry.
  • 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: NG-CR
Triple: [Odukpani, hasISO3166-2Code, NG-CR]
Generated description
NG-CR is the ISO 3166-2 subdivision code assigned to Cross River State in Nigeria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: NG-CR
Target entity description: NG-CR is the ISO 3166-2 subdivision code assigned to Cross River State in Nigeria.
  • A. crg
    crg is the ISO 639-3 language code for Michif, the mixed Cree–French language traditionally spoken by Métis communities in Canada and parts of the United States.
  • B. CR 527
    CR 527 is a county highway in New Jersey that runs through multiple counties, serving as a significant north–south arterial route.
  • C. NKG
    NKG is the IATA airport code for Nanjing Lukou International Airport, the main commercial airport serving Nanjing in eastern China.
  • D. CRCL
    CRCL is the Office for Civil Rights and Civil Liberties within the U.S. Department of Homeland Security, responsible for ensuring that civil rights and civil liberties are protected in the department’s policies and activities.
  • E. CRD
    CRD is a centralized online database maintained by FINRA that contains licensing and registration information on broker-dealers and their associated individuals in the U.S. financial industry.
  • 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_69d7bdf52b94819096d6f0ba4ab50a98 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96fb1c7248190bb6e644e041d192e completed April 10, 2026, 9:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68edaa6288190a775f6e852fa941b completed May 2, 2026, 11:55 p.m.
NEDg Description generation batch_69f6900385548190befe667dc4e33af9 completed May 3, 2026, midnight
NED2 Entity disambiguation (via description) batch_69f690c0bd208190bd1f04a9640ad1ce completed May 3, 2026, 12:03 a.m.
Created at: April 9, 2026, 5:34 p.m.