Triple

T29750844

Position	Surface form	Disambiguated ID	Type / Status
Subject	Bohemian Central Uplands	`E752888`	entity
Predicate	containsCastleRuins	`P71307`	FINISHED
Object	Hazmburk Castle Hazmburk Castle is a medieval hilltop fortress ruin in the Czech Republic, notable for its twin towers and commanding views over the surrounding Bohemian landscape.	`E1885457`	NE FINISHED

How this triple was built (3 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: Hazmburk Castle | Statement: [Bohemian Central Uplands, containsCastleRuins, Hazmburk 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: Hazmburk Castle
Triple: [Bohemian Central Uplands, containsCastleRuins, Hazmburk Castle]

Generated description

Hazmburk Castle is a medieval hilltop fortress ruin in the Czech Republic, notable for its twin towers and commanding views over the surrounding Bohemian landscape.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: containsCastleRuins
Context triple: [Bohemian Central Uplands, containsCastleRuins, Hazmburk Castle]

A. hasRuinsOn
Indicates that one location or object contains or is the site of ruins situated upon it.
B. hasCastleRemains chosen
Indicates that one entity possesses or contains the remaining structures or ruins of a castle associated with it.
C. hasMonasteryRuins
Indicates that an entity possesses or contains the remains or ruins of a former monastery.
D. hasFamousCastle
Indicates that an entity possesses or is the location of a castle that is widely recognized or renowned.
E. hasNumberOfChurchRuins
Indicates the quantity of church ruins associated with a given entity.
F. None of above.

Provenance (6 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_69feba0f09508190b3e871c62b19ec7f`	completed	May 9, 2026, 4:37 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a26e5e24eb08190934ef78347a317c8`	completed	June 8, 2026, 3:55 p.m.
NEDg	Description generation	`batch_6a26e68b913481908d53ac147ad34f74`	completed	June 8, 2026, 3:58 p.m.
NED2	Entity disambiguation (via description)	`batch_6a26e7057a0c819089535980d5b98484`	completed	June 8, 2026, 4 p.m.
PD	Predicate disambiguation	`batch_69feb957fe7c8190969fb31a6d1a59c8`	completed	May 9, 2026, 4:34 a.m.

Created at: April 28, 2026, 7:53 p.m.