Triple

T6415873
Position Surface form Disambiguated ID Type / Status
Subject Saint Martin (France) E127825 entity
Predicate ISO3166-1Alpha3 P189 FINISHED
Object MAF
MAF is the three-letter ISO 3166-1 alpha-3 country code assigned to the French overseas collectivity of Saint Martin in the Caribbean.
 E592421 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: MAF | Statement: [Saint Martin (France), ISO3166-1Alpha3, MAF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MAF
Context triple: [Saint Martin (France), ISO3166-1Alpha3, MAF]
  • A. MRAF
    MRAF is the highest rank in the Royal Air Force, equivalent to a five-star air officer and typically held only in wartime or as an honorary appointment.
  • B. MAB
    MAB is a German bibliographic data format used for cataloging and exchanging library records, closely related to and historically aligned with MARC standards.
  • C. MAM
    MAM is a prominent modern art museum in Mexico City known for its extensive collection of 20th- and 21st-century Mexican and international artworks.
  • D. MAU
    MAU (Media Access Unit) is a network device used in IEEE 802.5 Token Ring networks to connect multiple stations and manage the ring’s physical topology.
  • E. MCF
    MCF is the IATA airport code for the military airfield serving MacDill Air Force Base in Tampa, Florida.
  • 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: MAF
Triple: [Saint Martin (France), ISO3166-1Alpha3, MAF]
Generated description
MAF is the three-letter ISO 3166-1 alpha-3 country code assigned to the French overseas collectivity of Saint Martin in the Caribbean.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MAF
Target entity description: MAF is the three-letter ISO 3166-1 alpha-3 country code assigned to the French overseas collectivity of Saint Martin in the Caribbean.
  • A. MRAF
    MRAF is the highest rank in the Royal Air Force, equivalent to a five-star air officer and typically held only in wartime or as an honorary appointment.
  • B. MAB
    MAB is a German bibliographic data format used for cataloging and exchanging library records, closely related to and historically aligned with MARC standards.
  • C. MAM
    MAM is a prominent modern art museum in Mexico City known for its extensive collection of 20th- and 21st-century Mexican and international artworks.
  • D. MAU
    MAU (Media Access Unit) is a network device used in IEEE 802.5 Token Ring networks to connect multiple stations and manage the ring’s physical topology.
  • E. MCF
    MCF is the IATA airport code for the military airfield serving MacDill Air Force Base in Tampa, Florida.
  • 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_69c0083815208190a9b299b8e0640218 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c068e89c2c81909eeedc234e8ccde2 completed March 22, 2026, 10:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c640caaed881908ff9863b1b792ebc completed March 27, 2026, 8:33 a.m.
NEDg Description generation batch_69c641d6024c8190996aae40851a3b73 completed March 27, 2026, 8:37 a.m.
NED2 Entity disambiguation (via description) batch_69c6425e0a348190bc1eb90eb8c00597 completed March 27, 2026, 8:39 a.m.
Created at: March 22, 2026, 4:42 p.m.