Triple

T27428318
Position Surface form Disambiguated ID Type / Status
Subject Londerzeel E690552 entity
Predicate hasRailwayStation P918 FINISHED
Object Londerzeel railway station
Londerzeel railway station is a local train station in the town of Londerzeel, Belgium, providing regional rail connections for commuters and travelers.
E1773894 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: Londerzeel railway station | Statement: [Londerzeel, hasRailwayStation, Londerzeel railway station]
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: Londerzeel railway station
Triple: [Londerzeel, hasRailwayStation, Londerzeel railway station]
Generated description
Londerzeel railway station is a local train station in the town of Londerzeel, Belgium, providing regional rail connections for commuters and travelers.

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_69ef52003fb48190b0f1295246182a86 completed April 27, 2026, 12:09 p.m.
NER Named-entity recognition batch_69f62d570d548190b7f696646baee862 completed May 2, 2026, 4:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12b24eac488190a25d1fec723693f7 completed May 24, 2026, 8:09 a.m.
NEDg Description generation batch_6a12b54f5fe48190b6d5ff48cedf1511 completed May 24, 2026, 8:22 a.m.
NED2 Entity disambiguation (via description) batch_6a12b5db2f1c819088f009de0c26ed32 completed May 24, 2026, 8:24 a.m.
Created at: April 27, 2026, 12:41 p.m.