Triple

T19459380
Position Surface form Disambiguated ID Type / Status
Subject Ua Huka E486825 entity
Predicate ISO3166-1Alpha2 P189 FINISHED
Object PF
PF is the ISO 3166-1 alpha-2 country code for French Polynesia, an overseas collectivity of France in the South Pacific Ocean.
 E757059 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: PF | Statement: [Ua Huka, ISO3166-1Alpha2, PF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PF
Context triple: [Ua Huka, ISO3166-1Alpha2, PF]
  • A. PF
    PF is the vehicle registration code used on license plates for the German city of Pforzheim.
  • B. FP
    FP is the station code for Fehrbelliner Platz, a public transit station in Berlin, Germany.
  • C. FP
    FP is the station code for Floral Park station on the Long Island Rail Road in New York.
  • D. PW
    PW is the abbreviation for "The Professional Web," a term typically referring to the ecosystem of standards, tools, and practices used to build and maintain modern, production-quality websites and web applications.
  • E. PW
    PW is the commonly used nickname of P. W. Botha, the former South African prime minister and state president during the apartheid era.
  • 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: PF
Triple: [Ua Huka, ISO3166-1Alpha2, PF]
Generated description
PF is the ISO 3166-1 alpha-2 country code for French Polynesia, an overseas collectivity of France in the South Pacific Ocean.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PF
Target entity description: PF is the ISO 3166-1 alpha-2 country code for French Polynesia, an overseas collectivity of France in the South Pacific Ocean.
  • A. PF chosen
    PF is the vehicle registration code used on license plates for the German city of Pforzheim.
  • B. FP
    FP is the station code for Fehrbelliner Platz, a public transit station in Berlin, Germany.
  • C. FP
    FP is the station code for Floral Park station on the Long Island Rail Road in New York.
  • D. PW
    PW is the abbreviation for "The Professional Web," a term typically referring to the ecosystem of standards, tools, and practices used to build and maintain modern, production-quality websites and web applications.
  • E. PW
    PW is the commonly used nickname of P. W. Botha, the former South African prime minister and state president during the apartheid era.
  • F. None of above.

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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633c6c55c8190965ada884f17c800 completed April 20, 2026, 2:10 p.m.
NED1 Entity disambiguation (via context triple) batch_6a073b3a5ce88190a35e6b6195c5ca02 completed May 15, 2026, 3:26 p.m.
NEDg Description generation batch_6a073c0a02c8819080b0e71caf65e6fa completed May 15, 2026, 3:30 p.m.
NED2 Entity disambiguation (via description) batch_6a073d0e92d48190880317263fe6e481 completed May 15, 2026, 3:34 p.m.
Created at: April 10, 2026, 1:38 p.m.