Triple

T34549698
Position Surface form Disambiguated ID Type / Status
Subject Santa Cruz de Bezana E887027 entity
Predicate hasTransportConnection P845 FINISHED
Object S-20 highway
The S-20 highway is a Spanish road that serves as a key access route to the city of Santander and its surrounding municipalities in Cantabria.
 E2153779 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: S-20 highway | Statement: [Santa Cruz de Bezana, hasTransportConnection, S-20 highway]
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: S-20 highway
Triple: [Santa Cruz de Bezana, hasTransportConnection, S-20 highway]
Generated description
The S-20 highway is a Spanish road that serves as a key access route to the city of Santander and its surrounding municipalities in Cantabria.

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_69f349cff89081908f91e0b064f4833e completed April 30, 2026, 12:23 p.m.
NER Named-entity recognition batch_69f72024a3348190b5e21ba600e64bb4 completed May 3, 2026, 10:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a387cf1180081909359cffa1e63f118 completed June 22, 2026, 12:08 a.m.
NEDg Description generation batch_6a387e456b2881908c70545f1a103dd2 completed June 22, 2026, 12:13 a.m.
NED2 Entity disambiguation (via description) batch_6a387ebe432c8190848a35a2695d2204 completed June 22, 2026, 12:15 a.m.
Created at: May 1, 2026, 2:02 a.m.