Triple

T15267530
Position Surface form Disambiguated ID Type / Status
Subject Petronas Dagangan Berhad E364937 entity
Predicate shortName P43 FINISHED
Object PDB
PDB is the commonly used abbreviation for Petronas Dagangan Berhad, the principal domestic marketing arm of Malaysia’s national oil company, PETRONAS.
 E1147092 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: PDB | Statement: [Petronas Dagangan Berhad, shortName, PDB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PDB
Context triple: [Petronas Dagangan Berhad, shortName, PDB]
  • A. PDB
    PDB (Program Database) is a file format used by Microsoft development tools to store debugging and project state information for compiled programs.
  • B. pdb
    pdb is Python’s built-in interactive debugger, used to inspect and control the execution of Python programs for troubleshooting and development.
  • C. Protein Data Bank
    The Protein Data Bank is a global repository that archives and provides open access to 3D structural data of biological macromolecules such as proteins and nucleic acids.
  • D. EMBL-EBI AlphaFold Protein Structure Database
    The EMBL-EBI AlphaFold Protein Structure Database is a publicly accessible resource providing predicted 3D structures of proteins generated by DeepMind’s AlphaFold system.
  • E. UniParc
    UniParc is a comprehensive, non-redundant archive that stores and tracks all known unique protein sequences from multiple sources over time.
  • 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: PDB
Triple: [Petronas Dagangan Berhad, shortName, PDB]
Generated description
PDB is the commonly used abbreviation for Petronas Dagangan Berhad, the principal domestic marketing arm of Malaysia’s national oil company, PETRONAS.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PDB
Target entity description: PDB is the commonly used abbreviation for Petronas Dagangan Berhad, the principal domestic marketing arm of Malaysia’s national oil company, PETRONAS.
  • A. PDB
    PDB (Program Database) is a file format used by Microsoft development tools to store debugging and project state information for compiled programs.
  • B. pdb
    pdb is Python’s built-in interactive debugger, used to inspect and control the execution of Python programs for troubleshooting and development.
  • C. Protein Data Bank
    The Protein Data Bank is a global repository that archives and provides open access to 3D structural data of biological macromolecules such as proteins and nucleic acids.
  • D. EMBL-EBI AlphaFold Protein Structure Database
    The EMBL-EBI AlphaFold Protein Structure Database is a publicly accessible resource providing predicted 3D structures of proteins generated by DeepMind’s AlphaFold system.
  • E. UniParc
    UniParc is a comprehensive, non-redundant archive that stores and tracks all known unique protein sequences from multiple sources over time.
  • 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_69d85a0f08408190b3c3259ae35d79d2 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0094ca9ac8190a1f97a7b74c96cd5 completed April 15, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69fee602067c81908b1aaaca8871eeb9 completed May 9, 2026, 7:45 a.m.
NEDg Description generation batch_69fee6b1a29481908c5c945ef801468d completed May 9, 2026, 7:48 a.m.
NED2 Entity disambiguation (via description) batch_69fee7b5e3f0819091246455e239996a completed May 9, 2026, 7:52 a.m.
Created at: April 10, 2026, 3:14 a.m.