Triple

T12011786
Position Surface form Disambiguated ID Type / Status
Subject Differential Topology (book) E285920 entity
Predicate abbreviation P43 FINISHED
Object GTM 33
GTM 33 is the standard abbreviation for the influential graduate-level textbook "Differential Topology" in Springer’s Graduate Texts in Mathematics series.
 E960597 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: GTM 33 | Statement: [Differential Topology (book), abbreviation, GTM 33]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GTM 33
Context triple: [Differential Topology (book), abbreviation, GTM 33]
  • A. GTM
    GTM is the three-letter ISO 3166-1 alpha-3 country code assigned to Guatemala.
  • B. GTM
    GTM was a former name of Vinci, the major French concessions and construction company involved in large-scale infrastructure projects worldwide.
  • C. GA3
    GA3 is the standard abbreviated designation for Georgia’s 3rd congressional district in the United States House of Representatives.
  • D. Google Tag Manager
    Google Tag Manager is a tag management system that lets marketers and developers easily add, update, and manage tracking and analytics tags on websites and apps without modifying the underlying code directly.
  • E. IAB Tech Lab
    IAB Tech Lab is a global industry body that develops technical standards and solutions to support and improve digital advertising.
  • 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: GTM 33
Triple: [Differential Topology (book), abbreviation, GTM 33]
Generated description
GTM 33 is the standard abbreviation for the influential graduate-level textbook "Differential Topology" in Springer’s Graduate Texts in Mathematics series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GTM 33
Target entity description: GTM 33 is the standard abbreviation for the influential graduate-level textbook "Differential Topology" in Springer’s Graduate Texts in Mathematics series.
  • A. GTM
    GTM is the three-letter ISO 3166-1 alpha-3 country code assigned to Guatemala.
  • B. GTM
    GTM was a former name of Vinci, the major French concessions and construction company involved in large-scale infrastructure projects worldwide.
  • C. GA3
    GA3 is the standard abbreviated designation for Georgia’s 3rd congressional district in the United States House of Representatives.
  • D. Google Tag Manager
    Google Tag Manager is a tag management system that lets marketers and developers easily add, update, and manage tracking and analytics tags on websites and apps without modifying the underlying code directly.
  • E. IAB Tech Lab
    IAB Tech Lab is a global industry body that develops technical standards and solutions to support and improve digital advertising.
  • 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_69d6ab45a368819084fce08bf0dc3705 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903d7777481908cd5a001f75e2ee3 completed April 10, 2026, 2:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69f48b363c6481908c8414c1eecc14f5 completed May 1, 2026, 11:15 a.m.
NEDg Description generation batch_69f48fc6da4c81908442f18cb4a65b27 completed May 1, 2026, 11:34 a.m.
NED2 Entity disambiguation (via description) batch_69f495cc50908190aab4f8ca64c66ef3 completed May 1, 2026, noon
Created at: April 8, 2026, 9:46 p.m.