Triple

T4525989
Position Surface form Disambiguated ID Type / Status
Subject Agence France-Presse E103378 entity
Predicate hasAbbreviation P43 FINISHED
Object AFP
AFP is a major international news agency based in Paris that provides global news coverage in multiple languages.
E450008 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: AFP | Statement: [Agence France-Presse, hasAbbreviation, AFP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AFP
Context triple: [Agence France-Presse, hasAbbreviation, AFP]
  • A. AFP
    AFP is the unified military organization responsible for the defense and security of the Republic of the Philippines.
  • B. AFP
    AFP (Apple Filing Protocol) is a network protocol developed by Apple for file services and sharing primarily on macOS and classic Mac OS systems.
  • C. ADF
    ADF is the abbreviation for the Australian Defence Force, the unified military organization responsible for defending Australia and its national interests.
  • D. AF
    AF is the two-letter ISO 3166-1 alpha-2 country code assigned to Afghanistan for international standardization and referencing.
  • E. AF
    AF is the two-letter IATA airline designator assigned to Air France, the flag carrier of France.
  • 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: AFP
Triple: [Agence France-Presse, hasAbbreviation, AFP]
Generated description
AFP is a major international news agency based in Paris that provides global news coverage in multiple languages.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: AFP
Target entity description: AFP is a major international news agency based in Paris that provides global news coverage in multiple languages.
  • A. AFP
    AFP (Apple Filing Protocol) is a network protocol developed by Apple for file services and sharing primarily on macOS and classic Mac OS systems.
  • B. AFP
    AFP is the unified military organization responsible for the defense and security of the Republic of the Philippines.
  • C. ADF
    ADF is the abbreviation for the Australian Defence Force, the unified military organization responsible for defending Australia and its national interests.
  • D. AF
    AF is the two-letter ISO 3166-1 alpha-2 country code assigned to Afghanistan for international standardization and referencing.
  • E. AF
    AF is the two-letter IATA airline designator assigned to Air France, the flag carrier of France.
  • 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_69bd43dba59881908cf59b31df8c7ae1 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd577490f48190ac1fb3cbf3d8a41e completed March 20, 2026, 2:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69bda44fcec48190a1430b4e74ec30fb completed March 20, 2026, 7:47 p.m.
NEDg Description generation batch_69bda5b564648190ab2badb264910185 completed March 20, 2026, 7:53 p.m.
NED2 Entity disambiguation (via description) batch_69bda658568c8190bf97e4328e3799be completed March 20, 2026, 7:56 p.m.
Created at: March 20, 2026, 1:03 p.m.