Triple

T34888382

Position	Surface form	Disambiguated ID	Type / Status
Subject	Parc national de l’Île-Bonaventure-et-du-Rocher-Percé	`E1006212`	entity
Predicate	hasPart	`P35`	FINISHED
Object	Rocher Percé Rocher Percé is a famous natural limestone arch and sea stack off the coast of the Gaspé Peninsula in Quebec, Canada, renowned as a striking coastal landmark and tourist attraction.	`E2119681`	NE FINISHED

How this triple was built (2 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: Rocher Percé | Statement: [Parc national de l’Île-Bonaventure-et-du-Rocher-Percé, hasPart, Rocher Percé]

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: Rocher Percé
Triple: [Parc national de l’Île-Bonaventure-et-du-Rocher-Percé, hasPart, Rocher Percé]

Generated description

Rocher Percé is a famous natural limestone arch and sea stack off the coast of the Gaspé Peninsula in Quebec, Canada, renowned as a striking coastal landmark and tourist attraction.

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_69f76dbedb288190afe5780710847410`	completed	May 3, 2026, 3:46 p.m.
NER	Named-entity recognition	`batch_69f781bc62788190897f069664a4260b`	completed	May 3, 2026, 5:11 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a37b25de02c8190956d5698dbabf474`	completed	June 21, 2026, 9:43 a.m.
NEDg	Description generation	`batch_6a37b2e1a20c8190a5012a40d0fc54de`	completed	June 21, 2026, 9:46 a.m.
NED2	Entity disambiguation (via description)	`batch_6a37b396617c8190bc3fd123f565447a`	completed	June 21, 2026, 9:49 a.m.

Created at: May 3, 2026, 4 p.m.