Triple

T30287083

Position	Surface form	Disambiguated ID	Type / Status
Subject	Trinity College Dublin Chapel	`E770266`	entity
Predicate	hasChoralTradition	`P4009`	FINISHED
Object	Trinity College Dublin Chapel Choir Trinity College Dublin Chapel Choir is the resident liturgical and concert choir of Trinity College Dublin’s chapel, known for its choral performances within the university’s historic religious and ceremonial life.	`E1907772`	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: Trinity College Dublin Chapel Choir | Statement: [Trinity College Dublin Chapel, hasChoralTradition, Trinity College Dublin Chapel Choir]

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: Trinity College Dublin Chapel Choir
Triple: [Trinity College Dublin Chapel, hasChoralTradition, Trinity College Dublin Chapel Choir]

Generated description

Trinity College Dublin Chapel Choir is the resident liturgical and concert choir of Trinity College Dublin’s chapel, known for its choral performances within the university’s historic religious and ceremonial life.

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

Target predicate: hasChoralTradition
Context triple: [Trinity College Dublin Chapel, hasChoralTradition, Trinity College Dublin Chapel Choir]

A. hasChoralArrangement
Indicates that one entity is a choral arrangement version or setting of another entity (typically an original musical work).
B. usesChorale
Indicates that one entity incorporates or employs a chorale (a hymn-like musical piece) within its structure or content.
C. hasChoir chosen
Indicates that an entity possesses, maintains, or is associated with a choir.
D. hasChorusMelodyOrigin
Indicates that the origin or source of a chorus melody is attributed or linked to a particular entity.
E. hasChoralFoundation
Indicates that an entity possesses or is associated with an established choral institution or choir as a formal foundation.
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_69f224875c288190a9b96b975006ec4a`	completed	April 29, 2026, 3:32 p.m.
NER	Named-entity recognition	`batch_69fcef654d588190b29ecc76678d1aa0`	completed	May 7, 2026, 8 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a276f02b5d48190a117a5f44c256777`	completed	June 9, 2026, 1:40 a.m.
NEDg	Description generation	`batch_6a2770df1ad0819086765e65f48c9b62`	completed	June 9, 2026, 1:48 a.m.
NED2	Entity disambiguation (via description)	`batch_6a277142b980819086dcc10c93592afe`	completed	June 9, 2026, 1:49 a.m.
PD	Predicate disambiguation	`batch_69fcecdb97f48190b382b7d13be92dc0`	completed	May 7, 2026, 7:49 p.m.

Created at: April 29, 2026, 7:46 p.m.