Triple

T2001158
Position Surface form Disambiguated ID Type / Status
Subject Subcommittee on Prevention of Torture E43473 entity
Predicate shortName P43 FINISHED
Object SPT
SPT is the United Nations Subcommittee on Prevention of Torture, a treaty body that monitors places of detention worldwide to prevent torture and ill-treatment.
 E223979 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: SPT | Statement: [Subcommittee on Prevention of Torture, shortName, SPT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SPT
Context triple: [Subcommittee on Prevention of Torture, shortName, SPT]
  • A. SPS
    SPS is a high-energy circular particle accelerator at CERN that serves as a key injector for the Large Hadron Collider and supports a wide range of physics experiments.
  • B. SPP
    SPP is the Supreme People's Procuratorate of China, the highest national agency responsible for legal prosecution and supervision of law enforcement in the country.
  • C. SP
    SP is the official aircraft registration prefix used to identify airplanes registered in Poland.
  • D. PT
    PT is the time standard used along the west coast of North America, including cities like Los Angeles, San Francisco, and Vancouver.
  • E. PT
    PT is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Portugal 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: SPT
Triple: [Subcommittee on Prevention of Torture, shortName, SPT]
Generated description
SPT is the United Nations Subcommittee on Prevention of Torture, a treaty body that monitors places of detention worldwide to prevent torture and ill-treatment.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SPT
Target entity description: SPT is the United Nations Subcommittee on Prevention of Torture, a treaty body that monitors places of detention worldwide to prevent torture and ill-treatment.
  • A. SPS
    SPS is a high-energy circular particle accelerator at CERN that serves as a key injector for the Large Hadron Collider and supports a wide range of physics experiments.
  • B. SPP
    SPP is the Supreme People's Procuratorate of China, the highest national agency responsible for legal prosecution and supervision of law enforcement in the country.
  • C. SP
    SP is the official aircraft registration prefix used to identify airplanes registered in Poland.
  • D. PT
    PT is the time standard used along the west coast of North America, including cities like Los Angeles, San Francisco, and Vancouver.
  • E. PT
    PT is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Portugal 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_69a88715dbbc8190b2299e29e955d997 completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb880c710819098fb877052ce56dc completed March 7, 2026, 5:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae0342ef8c8190b7771076282981c3 completed March 8, 2026, 11:16 p.m.
NEDg Description generation batch_69ae057cc1a08190895031fa6c095f49 completed March 8, 2026, 11:25 p.m.
NED2 Entity disambiguation (via description) batch_69ae0751eff4819086e5469a2c56a24d completed March 8, 2026, 11:33 p.m.
Created at: March 4, 2026, 7:37 p.m.