Triple

T38607015
Position Surface form Disambiguated ID Type / Status
Subject Glacier Blanc E934369 entity
Predicate hasRouteTo P4374 FINISHED
Object Refuge du Glacier Blanc
Refuge du Glacier Blanc is a high-altitude mountain hut in the French Alps that serves as a popular base for hikers and climbers exploring the Glacier Blanc area.
E2276109 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: Refuge du Glacier Blanc | Statement: [Glacier Blanc, hasRouteTo, Refuge du Glacier Blanc]
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: Refuge du Glacier Blanc
Triple: [Glacier Blanc, hasRouteTo, Refuge du Glacier Blanc]
Generated description
Refuge du Glacier Blanc is a high-altitude mountain hut in the French Alps that serves as a popular base for hikers and climbers exploring the Glacier Blanc area.

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_69f76eccd6d081909ccce171011739a1 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fcd95a54548190b0272da94449b29a completed May 7, 2026, 6:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a41eaac6adc81909aab5ae41590237d completed June 29, 2026, 3:46 a.m.
NEDg Description generation batch_6a41eb3a46008190b64f71f254890bec completed June 29, 2026, 3:49 a.m.
NED2 Entity disambiguation (via description) batch_6a41ebbcc9dc81908c568a8a4603dfb2 completed June 29, 2026, 3:51 a.m.
Created at: May 3, 2026, 4:32 p.m.