Triple

T27860580
Position Surface form Disambiguated ID Type / Status
Subject Antwerp churches E704216 entity
Predicate contains P35 FINISHED
Object Church of Saint George (Antwerp)
The Church of Saint George in Antwerp is a historic Roman Catholic church known for its neo-Gothic architecture and richly decorated interior.
 E1808272 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: Church of Saint George (Antwerp) | Statement: [Antwerp churches, contains, Church of Saint George (Antwerp)]
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: Church of Saint George (Antwerp)
Triple: [Antwerp churches, contains, Church of Saint George (Antwerp)]
Generated description
The Church of Saint George in Antwerp is a historic Roman Catholic church known for its neo-Gothic architecture and richly decorated interior.

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_69ef840f12408190b539d00d79658abf completed April 27, 2026, 3:43 p.m.
NER Named-entity recognition batch_69f6394220d88190a9d7d5f5ebcf5e4f completed May 2, 2026, 5:49 p.m.
NED1 Entity disambiguation (via context triple) batch_6a15e68c1ee0819087523902ffa6822c completed May 26, 2026, 6:29 p.m.
NEDg Description generation batch_6a15e7ebbe3c8190886a959072625fa0 completed May 26, 2026, 6:35 p.m.
NED2 Entity disambiguation (via description) batch_6a15ed5b346c8190888ef61373cee561 completed May 26, 2026, 6:58 p.m.
Created at: April 27, 2026, 6:17 p.m.