Triple

T29750845
Position Surface form Disambiguated ID Type / Status
Subject Bohemian Central Uplands E752888 entity
Predicate containsCastleRuins P71307 FINISHED
Object Kostomlaty Castle
Kostomlaty Castle is a medieval hilltop fortress ruin in the Bohemian Central Uplands of the Czech Republic, known for its scenic views and historical significance.
E1888719 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: Kostomlaty Castle | Statement: [Bohemian Central Uplands, containsCastleRuins, Kostomlaty Castle]
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: Kostomlaty Castle
Triple: [Bohemian Central Uplands, containsCastleRuins, Kostomlaty Castle]
Generated description
Kostomlaty Castle is a medieval hilltop fortress ruin in the Bohemian Central Uplands of the Czech Republic, known for its scenic views and historical significance.

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_69f0d62c84cc8190846f80ae04fdf8ec completed April 28, 2026, 3:45 p.m.
NER Named-entity recognition batch_69febad292448190949553dd2658709a completed May 9, 2026, 4:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a26f1b1bf208190953a11d1fcfc8a78 completed June 8, 2026, 4:45 p.m.
NEDg Description generation batch_6a26f31d6d088190980cb60d9ea41d4d completed June 8, 2026, 4:51 p.m.
NED2 Entity disambiguation (via description) batch_6a26f4247b04819084468924f9da4df4 completed June 8, 2026, 4:56 p.m.
Created at: April 28, 2026, 7:53 p.m.