Triple

T7938702
Position Surface form Disambiguated ID Type / Status
Subject Pulp E184340 entity
Predicate hasComponent P35 FINISHED
Object Pulp API
Pulp API is the RESTful interface of the Pulp content management and distribution platform, enabling programmatic management of software repositories and content.
E699789 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: Pulp API | Statement: [Pulp, hasComponent, Pulp API]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pulp API
Context triple: [Pulp, hasComponent, Pulp API]
  • A. Poplar SDK
    Poplar SDK is Graphcore’s specialized software toolkit designed to program and optimize machine learning workloads on its Intelligence Processing Unit (IPU) hardware.
  • B. PULSE network
    PULSE network is a major U.S. electronic funds transfer and debit payment network widely used for ATM and point-of-sale transactions.
  • C. PUS
    PUS is the IATA airport code for Gimhae International Airport serving the Busan metropolitan area in South Korea.
  • D. Pallets Projects
    Pallets Projects is an open-source organization best known for creating and maintaining the Flask web framework and related Python tooling.
  • E. PAP
    PAP is the legislative body of the African Union that aims to promote democracy, human rights, and integration across African states.
  • 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: Pulp API
Triple: [Pulp, hasComponent, Pulp API]
Generated description
Pulp API is the RESTful interface of the Pulp content management and distribution platform, enabling programmatic management of software repositories and content.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pulp API
Target entity description: Pulp API is the RESTful interface of the Pulp content management and distribution platform, enabling programmatic management of software repositories and content.
  • A. Poplar SDK
    Poplar SDK is Graphcore’s specialized software toolkit designed to program and optimize machine learning workloads on its Intelligence Processing Unit (IPU) hardware.
  • B. PULSE network
    PULSE network is a major U.S. electronic funds transfer and debit payment network widely used for ATM and point-of-sale transactions.
  • C. PUS
    PUS is the IATA airport code for Gimhae International Airport serving the Busan metropolitan area in South Korea.
  • D. Pallets Projects
    Pallets Projects is an open-source organization best known for creating and maintaining the Flask web framework and related Python tooling.
  • E. PAP
    PAP is the legislative body of the African Union that aims to promote democracy, human rights, and integration across African states.
  • 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_69ca8290c21c8190906a5ca6fe2b03c4 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3af0a2048190838d1aeda59fda0b completed March 31, 2026, 3:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5c0e868481908748d340244ea8ea completed March 31, 2026, 5:30 a.m.
NEDg Description generation batch_69cb7634f4dc8190b5e537f24bccd651 completed March 31, 2026, 7:22 a.m.
NED2 Entity disambiguation (via description) batch_69cbb67e77a48190b93c6ba61becfac4 completed March 31, 2026, 11:56 a.m.
Created at: March 30, 2026, 5:08 p.m.