Triple

T32093112

Position	Surface form	Disambiguated ID	Type / Status
Subject	2017 British & Irish Lions tour to New Zealand	`E819647`	entity
Predicate	attackCoach	`P117597`	FINISHED
Object	Rob Howley Rob Howley is a former Welsh international scrum-half who became a prominent rugby union coach, notably serving as an assistant and attack coach for Wales and the British & Irish Lions.	`E1993252`	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: Rob Howley | Statement: [2017 British & Irish Lions tour to New Zealand, attackCoach, Rob Howley]

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: Rob Howley
Triple: [2017 British & Irish Lions tour to New Zealand, attackCoach, Rob Howley]

Generated description

Rob Howley is a former Welsh international scrum-half who became a prominent rugby union coach, notably serving as an assistant and attack coach for Wales and the British & Irish Lions.

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

Target predicate: attackCoach
Context triple: [2017 British & Irish Lions tour to New Zealand, attackCoach, Rob Howley]

A. assistantCoachAt
Indicates that one entity serves in the role of assistant coach for a sports team, organization, or program represented by the other entity.
B. movementCoach
Indicates a relationship where one entity serves as a coach or instructor guiding another entity’s physical movement or movement-related skills.
C. assistantCoachTo
Indicates that one entity serves in the role of assistant coach to another entity, typically supporting and working under the primary coach.
D. homeCoach
Indicates that a person serves as the coach of the home team in a particular game or competition.
E. offensiveCoach chosen
Indicates that one entity serves as the offensive coach (responsible for directing the offense) for another entity, typically a sports team or player.
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_69f349004b2481908ce2e50af0d579a8`	completed	April 30, 2026, 12:20 p.m.
NER	Named-entity recognition	`batch_69f6b967d5308190bbb66d0a8dd52612`	completed	May 3, 2026, 2:56 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a2f011deb8c8190b11550ccfcd800af`	completed	June 14, 2026, 7:29 p.m.
NEDg	Description generation	`batch_6a2f02648898819098c5a1150a984dd5`	completed	June 14, 2026, 7:35 p.m.
NED2	Entity disambiguation (via description)	`batch_6a2f03669a7c8190b928b260ef9f6454`	completed	June 14, 2026, 7:39 p.m.
PD	Predicate disambiguation	`batch_69f6b6293188819080d5041ca0adb969`	completed	May 3, 2026, 2:42 a.m.

Created at: May 1, 2026, 12:25 a.m.