Triple

T145519
Position Surface form Disambiguated ID Type / Status
Subject Northern Mariana Islands E2944 entity
Predicate ISO3166-1Alpha2 P189 FINISHED
Object MP
MP is the two-letter ISO 3166-1 alpha-2 country code assigned to the Northern Mariana Islands.
 E17026 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: MP | Statement: [Northern Mariana Islands, ISO3166-1Alpha2, MP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MP
Context triple: [Northern Mariana Islands, ISO3166-1Alpha2, MP]
  • A. MC
    MC is the official abbreviation for NATO’s highest military authority, the NATO Military Committee.
  • B. PM
    PM is the standard abbreviation for *Principia Mathematica*, the landmark three-volume work on the foundations of mathematics and logic by Alfred North Whitehead and Bertrand Russell.
  • C. MX
    MX is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Mexico in international standards and systems.
  • D. PT
    PT is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Portugal in international standards and systems.
  • E. PK
    PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
  • 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: MP
Triple: [Northern Mariana Islands, ISO3166-1Alpha2, MP]
Generated description
MP is the two-letter ISO 3166-1 alpha-2 country code assigned to the Northern Mariana Islands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MP
Target entity description: MP is the two-letter ISO 3166-1 alpha-2 country code assigned to the Northern Mariana Islands.
  • A. MC
    MC is the official abbreviation for NATO’s highest military authority, the NATO Military Committee.
  • B. PM
    PM is the standard abbreviation for *Principia Mathematica*, the landmark three-volume work on the foundations of mathematics and logic by Alfred North Whitehead and Bertrand Russell.
  • C. MX
    MX is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Mexico in international standards and systems.
  • D. PT
    PT is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Portugal in international standards and systems.
  • E. PK
    PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
  • 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_69a2521e35c08190b28e5c9f1e3c9b59 completed Feb. 28, 2026, 2:25 a.m.
NER Named-entity recognition batch_69a257ea7eac8190884a53453a9e0dd6 completed Feb. 28, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2bf69fd2081908df35ea5ade4307c completed Feb. 28, 2026, 10:11 a.m.
NEDg Description generation batch_69a2bfb9ad848190ae1412d0e180f48f completed Feb. 28, 2026, 10:13 a.m.
NED2 Entity disambiguation (via description) batch_69a2c09721a88190a6268360c34a0b01 completed Feb. 28, 2026, 10:16 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.