Triple

T1534736
Position Surface form Disambiguated ID Type / Status
Subject Brown & Williamson E32524 entity
Predicate notableProduct P1448 FINISHED
Object GPC
GPC is a discount cigarette brand produced by the tobacco company Brown & Williamson.
 E174542 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: GPC | Statement: [Brown & Williamson, notableProduct, GPC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GPC
Context triple: [Brown & Williamson, notableProduct, GPC]
  • A. GPC
    GPC is the GNU Pascal Compiler, a free, open-source Pascal compiler that is part of the GNU Compiler Collection (GCC) project.
  • B. GP
    GP is the two-letter ISO 3166-1 alpha-2 country code assigned to Guadeloupe.
  • C. GAC
    The GAC is a committee within the Internet Corporation for Assigned Names and Numbers (ICANN) that provides governments and intergovernmental organizations with a formal voice in global internet governance and policy development.
  • D. GN
    GN is a fast, meta-build system tool used primarily by the Chromium project to generate build files for Ninja.
  • E. GD
    GD is the vehicle registration code used on license plates for cars registered in the city of Gdańsk, Poland.
  • 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: GPC
Triple: [Brown & Williamson, notableProduct, GPC]
Generated description
GPC is a discount cigarette brand produced by the tobacco company Brown & Williamson.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GPC
Target entity description: GPC is a discount cigarette brand produced by the tobacco company Brown & Williamson.
  • A. GPC
    GPC is the GNU Pascal Compiler, a free, open-source Pascal compiler that is part of the GNU Compiler Collection (GCC) project.
  • B. GP
    GP is the two-letter ISO 3166-1 alpha-2 country code assigned to Guadeloupe.
  • C. GAC
    The GAC is a committee within the Internet Corporation for Assigned Names and Numbers (ICANN) that provides governments and intergovernmental organizations with a formal voice in global internet governance and policy development.
  • D. GN
    GN is a fast, meta-build system tool used primarily by the Chromium project to generate build files for Ninja.
  • E. GD
    GD is the vehicle registration code used on license plates for cars registered in the city of Gdańsk, Poland.
  • 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_69a885ea86308190998f6bc14bb91f8e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90828cdf08190aa404a0c11335c7b completed March 5, 2026, 4:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad295da0988190b1dc171bcdfe4d71 completed March 8, 2026, 7:46 a.m.
NEDg Description generation batch_69ad29dc9fd08190b67527f0662c92dc completed March 8, 2026, 7:48 a.m.
NED2 Entity disambiguation (via description) batch_69ad2a4d71a88190b67ed21beebbb479 completed March 8, 2026, 7:50 a.m.
Created at: March 4, 2026, 7:26 p.m.