Triple

T24517208
Position Surface form Disambiguated ID Type / Status
Subject Pale di San Martino E606406 entity
Predicate nearestTown P350 FINISHED
Object San Martino di Castrozza
San Martino di Castrozza is a mountain resort village in the Italian Dolomites, known for its alpine scenery and outdoor activities like skiing and hiking.
E1643550 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: San Martino di Castrozza | Statement: [Pale di San Martino, nearestTown, San Martino di Castrozza]
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: San Martino di Castrozza
Triple: [Pale di San Martino, nearestTown, San Martino di Castrozza]
Generated description
San Martino di Castrozza is a mountain resort village in the Italian Dolomites, known for its alpine scenery and outdoor activities like skiing and hiking.

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_69e2c4c725148190a4e41577c5cb409c completed April 17, 2026, 11:39 p.m.
NER Named-entity recognition batch_69f2a852223081908f3b99a409316f6b completed April 30, 2026, 12:54 a.m.
NED1 Entity disambiguation (via context triple) batch_6a10046b2b4c81909a9b23cb21210888 completed May 22, 2026, 7:23 a.m.
NEDg Description generation batch_6a10058109548190be272b118a847fb8 completed May 22, 2026, 7:28 a.m.
NED2 Entity disambiguation (via description) batch_6a1006162a308190a1c1ed715d0a6691 completed May 22, 2026, 7:30 a.m.
Created at: April 18, 2026, 2:24 a.m.