Triple

T24522305
Position Surface form Disambiguated ID Type / Status
Subject Ishida Mitsunari E606565 entity
Predicate castle P101962 FINISHED
Object Sawayama Castle
Sawayama Castle was a strategically important Sengoku-period mountain fortress in Ōmi Province, Japan, best known as the stronghold of the warlord Ishida Mitsunari before the Battle of Sekigahara.
E1706315 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: Sawayama Castle | Statement: [Ishida Mitsunari, castle, Sawayama 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: Sawayama Castle
Triple: [Ishida Mitsunari, castle, Sawayama Castle]
Generated description
Sawayama Castle was a strategically important Sengoku-period mountain fortress in Ōmi Province, Japan, best known as the stronghold of the warlord Ishida Mitsunari before the Battle of Sekigahara.

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_69e2c4c85778819085f5da9af3569ad5 completed April 17, 2026, 11:39 p.m.
NER Named-entity recognition batch_69f2a872c120819095c9d50722230d66 completed April 30, 2026, 12:55 a.m.
NED1 Entity disambiguation (via context triple) batch_6a111ad7daf481908dd4668784a83be0 completed May 23, 2026, 3:11 a.m.
NEDg Description generation batch_6a111ba170c881908916feb646df7338 completed May 23, 2026, 3:14 a.m.
NED2 Entity disambiguation (via description) batch_6a111c1129588190918ec8f98cad6fd4 completed May 23, 2026, 3:16 a.m.
Created at: April 18, 2026, 2:25 a.m.