Triple

T638708
Position Surface form Disambiguated ID Type / Status
Subject WGS84 E16682 entity
Predicate standardizedBy P1371 FINISHED
Object NGA
The NGA (National Geospatial-Intelligence Agency) is a U.S. government intelligence and combat support agency responsible for providing geospatial intelligence, mapping, and related standards for national security and defense.
 E79832 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: NGA | Statement: [WGS84, standardizedBy, NGA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: NGA
Context triple: [WGS84, standardizedBy, NGA]
  • A. NGA
    NGA is the three-letter FIFA country code used to represent the Nigeria national football team in international competitions and rankings.
  • B. NGA
    NGA is the commonly used abbreviation for the National Gallery of Australia, the country’s premier national art museum located in Canberra.
  • C. .ng
    .ng is the country code top-level domain (ccTLD) assigned to Nigeria for use in its internet addresses.
  • D. GAU
    GAU is an abbreviation commonly used for the University of Göttingen, a major research university in Göttingen, Germany.
  • E. NCTC
    NCTC is the U.S. government’s primary organization for integrating and analyzing terrorism-related intelligence and coordinating counterterrorism efforts across agencies.
  • 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: NGA
Triple: [WGS84, standardizedBy, NGA]
Generated description
The NGA (National Geospatial-Intelligence Agency) is a U.S. government intelligence and combat support agency responsible for providing geospatial intelligence, mapping, and related standards for national security and defense.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: NGA
Target entity description: The NGA (National Geospatial-Intelligence Agency) is a U.S. government intelligence and combat support agency responsible for providing geospatial intelligence, mapping, and related standards for national security and defense.
  • A. NGA
    NGA is the three-letter FIFA country code used to represent the Nigeria national football team in international competitions and rankings.
  • B. NGA
    NGA is the commonly used abbreviation for the National Gallery of Australia, the country’s premier national art museum located in Canberra.
  • C. .ng
    .ng is the country code top-level domain (ccTLD) assigned to Nigeria for use in its internet addresses.
  • D. GAU
    GAU is an abbreviation commonly used for the University of Göttingen, a major research university in Göttingen, Germany.
  • E. NCTC
    NCTC is the U.S. government’s primary organization for integrating and analyzing terrorism-related intelligence and coordinating counterterrorism efforts across agencies.
  • 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_69a4936be1c88190af56540324b57da7 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49ee95b188190a67b12e1899bcdda completed March 1, 2026, 8:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69a574076b30819090f086b42696bb35 completed March 2, 2026, 11:27 a.m.
NEDg Description generation batch_69a5748d5a4c8190b4f8fcbbae972b88 completed March 2, 2026, 11:29 a.m.
NED2 Entity disambiguation (via description) batch_69a574fb37348190b0979dad87e79e53 completed March 2, 2026, 11:31 a.m.
Created at: March 1, 2026, 7:35 p.m.