Triple

T27444934
Position Surface form Disambiguated ID Type / Status
Subject Arcueil E692246 entity
Predicate hasLandmark P105 FINISHED
Object Arcueil–Cachan railway viaduct
The Arcueil–Cachan railway viaduct is a historic multi-arch rail bridge in the southern suburbs of Paris, France, carrying train lines across the valleys between the communes of Arcueil and Cachan.
 E1773812 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: Arcueil–Cachan railway viaduct | Statement: [Arcueil, hasLandmark, Arcueil–Cachan railway viaduct]
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: Arcueil–Cachan railway viaduct
Triple: [Arcueil, hasLandmark, Arcueil–Cachan railway viaduct]
Generated description
The Arcueil–Cachan railway viaduct is a historic multi-arch rail bridge in the southern suburbs of Paris, France, carrying train lines across the valleys between the communes of Arcueil and Cachan.

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_69ef5206c9248190b5975c2a7f9d229c completed April 27, 2026, 12:09 p.m.
NER Named-entity recognition batch_69f62d90df98819084ea88ad56d524af completed May 2, 2026, 5 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12b259e0648190a43102b1d9948c59 completed May 24, 2026, 8:10 a.m.
NEDg Description generation batch_6a12b3f7b0748190bfa5a2c631d0836d completed May 24, 2026, 8:16 a.m.
NED2 Entity disambiguation (via description) batch_6a12b50444b88190947f0c2989954233 completed May 24, 2026, 8:21 a.m.
Created at: April 27, 2026, 12:46 p.m.