Triple

T36459110
Position Surface form Disambiguated ID Type / Status
Subject Comune di Moltrasio E898239 entity
Predicate governmentSeat P761 FINISHED
Object Moltrasio town hall
Moltrasio town hall is the main municipal building of the lakeside Italian village of Moltrasio in Lombardy, housing its local administrative offices and civic functions.
E2184873 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: Moltrasio town hall | Statement: [Comune di Moltrasio, governmentSeat, Moltrasio town hall]
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: Moltrasio town hall
Triple: [Comune di Moltrasio, governmentSeat, Moltrasio town hall]
Generated description
Moltrasio town hall is the main municipal building of the lakeside Italian village of Moltrasio in Lombardy, housing its local administrative offices and civic functions.

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_69f76e57f08481908593bd0bc34581c8 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69f7bdafde948190b516b33d0252febe completed May 3, 2026, 9:27 p.m.
NED1 Entity disambiguation (via context triple) batch_6a39cfcc7aa08190ba04e0a01d604837 completed June 23, 2026, 12:14 a.m.
NEDg Description generation batch_6a39d0973c4481909e3c41c76fe0461b completed June 23, 2026, 12:17 a.m.
NED2 Entity disambiguation (via description) batch_6a39d149d0c88190b232b80550967869 completed June 23, 2026, 12:20 a.m.
Created at: May 3, 2026, 4:10 p.m.