Triple

T31558285

Position	Surface form	Disambiguated ID	Type / Status
Subject	Dominik Grewe	`E805186`	entity
Predicate	thesisSupervisor	`P106372`	FINISHED
Object	Paul H. J. Kelly Paul H. J. Kelly is a British computer scientist known for his work on compilers, parallel programming, and high-performance computing, and for his long-standing academic role at Imperial College London.	`E1967004`	NE FINISHED

How this triple was built (3 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: Paul H. J. Kelly | Statement: [Dominik Grewe, thesisSupervisor, Paul H. J. Kelly]

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: Paul H. J. Kelly
Triple: [Dominik Grewe, thesisSupervisor, Paul H. J. Kelly]

Generated description

Paul H. J. Kelly is a British computer scientist known for his work on compilers, parallel programming, and high-performance computing, and for his long-standing academic role at Imperial College London.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: thesisSupervisor
Context triple: [Dominik Grewe, thesisSupervisor, Paul H. J. Kelly]

A. postdoctoralAdvisor
Indicates that one person served as the postdoctoral research advisor or mentor to another person.
B. thesisType
Indicates the specific category or kind of thesis associated with an academic work or degree.
C. hasDoctoralStudentsThrough
Indicates that one entity has doctoral students indirectly through another entity, such as via co-supervision, program affiliation, or intermediary supervision relationships.
D. academicAdvisorOfAuthor chosen
Indicates that one person serves as the academic advisor or mentor responsible for guiding the author in their scholarly or research activities.
E. thesisOf
Indicates that a particular work is the thesis authored by a specified person or associated with a specified degree or institution.
F. None of above.

Provenance (6 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_69f348d22e088190ad555d5bd42f9da0`	completed	April 30, 2026, 12:19 p.m.
NER	Named-entity recognition	`batch_69f6a8055f8081908f635fe04654b5fe`	completed	May 3, 2026, 1:42 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a2b2d95db388190bfe8b3533d0d5ebb`	completed	June 11, 2026, 9:50 p.m.
NEDg	Description generation	`batch_6a2b2e9b343481908bee17668e076ff0`	completed	June 11, 2026, 9:54 p.m.
NED2	Entity disambiguation (via description)	`batch_6a2b2fa035708190a8d4d200e092a156`	completed	June 11, 2026, 9:58 p.m.
PD	Predicate disambiguation	`batch_69f6a75656e081908739ed9e2f600e42`	completed	May 3, 2026, 1:39 a.m.

Created at: April 30, 2026, 10:14 p.m.