Triple

T34773002
Position Surface form Disambiguated ID Type / Status
Subject fortifications of La Rochelle E1002417 entity
Predicate hasPart P35 FINISHED
Object Porte de Cougnes
Porte de Cougnes is a historic city gate in La Rochelle, France, that once formed part of the town’s defensive fortifications.
E2111041 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: Porte de Cougnes | Statement: [fortifications of La Rochelle, hasPart, Porte de Cougnes]
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: Porte de Cougnes
Triple: [fortifications of La Rochelle, hasPart, Porte de Cougnes]
Generated description
Porte de Cougnes is a historic city gate in La Rochelle, France, that once formed part of the town’s defensive fortifications.

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_69f76db30a108190bb57ca95b873e5bb completed May 3, 2026, 3:45 p.m.
NER Named-entity recognition batch_69f77a3c0f1081908e3624e46651e6fd completed May 3, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a37663b51cc81908f96fe1ace529ccb completed June 21, 2026, 4:19 a.m.
NEDg Description generation batch_6a3766c62020819090092f8f0de60644 completed June 21, 2026, 4:21 a.m.
NED2 Entity disambiguation (via description) batch_6a37673026e881908b26f42f12f81b2f completed June 21, 2026, 4:23 a.m.
Created at: May 3, 2026, 3:59 p.m.