Triple

T30440436

Position	Surface form	Disambiguated ID	Type / Status
Subject	Soham murders	`E774424`	entity
Predicate	relatedInquiry	`P146490`	FINISHED
Object	Bichard Inquiry The Bichard Inquiry was a public investigation in the UK that examined police and child protection failures exposed by the Soham murders and led to major reforms in information sharing and vetting procedures.	`E1915328`	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: Bichard Inquiry | Statement: [Soham murders, relatedInquiry, Bichard Inquiry]

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: Bichard Inquiry
Triple: [Soham murders, relatedInquiry, Bichard Inquiry]

Generated description

The Bichard Inquiry was a public investigation in the UK that examined police and child protection failures exposed by the Soham murders and led to major reforms in information sharing and vetting procedures.

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

Target predicate: relatedInquiry
Context triple: [Soham murders, relatedInquiry, Bichard Inquiry]

A. relatedQuestion
Indicates that one question is connected to another by topic, context, or relevance, suggesting they are meaningfully associated.
B. relatedPass
Indicates that one pass is associated with or connected to another pass in some relevant way.
C. relatedInvestigationOf chosen
Indicates that one investigation is connected to, derived from, or concerned with another investigation or case.
D. relatedSuit
Indicates that one suit is associated or connected to another suit in a relevant or meaningful way.
E. relatedIntermediate
Indicates an indirect or intermediate relationship between two entities, typically via one or more other entities or steps rather than a direct connection.
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_69f22493ef9c8190ae8c2afcb7f994c8`	completed	April 29, 2026, 3:32 p.m.
NER	Named-entity recognition	`batch_6a02fcbe03d0819082d3dd715ed41623`	completed	May 12, 2026, 10:11 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a2798c1f3f08190aeb481c0c6a80485`	completed	June 9, 2026, 4:38 a.m.
NEDg	Description generation	`batch_6a279c3015cc8190aaeedc6222520b7b`	completed	June 9, 2026, 4:53 a.m.
NED2	Entity disambiguation (via description)	`batch_6a279ce453108190a68db27eb0b35665`	completed	June 9, 2026, 4:56 a.m.
PD	Predicate disambiguation	`batch_6a02fc62138081908d2dbc5db7541d13`	completed	May 12, 2026, 10:09 a.m.

Created at: April 29, 2026, 8:08 p.m.