Triple

T19285813
Position Surface form Disambiguated ID Type / Status
Subject Hiroshima Station E482306 entity
Predicate railwayLine P848 FINISHED
Object Hiroden Hakushima Line
The Hiroden Hakushima Line is a tram line in Hiroshima, Japan, operated by Hiroshima Electric Railway, connecting central Hiroshima with the Hakushima area.
E2038921 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: Hiroden Hakushima Line | Statement: [Hiroshima Station, railwayLine, Hiroden Hakushima Line]
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: Hiroden Hakushima Line
Triple: [Hiroshima Station, railwayLine, Hiroden Hakushima Line]
Generated description
The Hiroden Hakushima Line is a tram line in Hiroshima, Japan, operated by Hiroshima Electric Railway, connecting central Hiroshima with the Hakushima area.

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_69d8e8cf61b0819096fe3e4107827c4e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fc024a7081909a25d7cc4e048f79 completed April 20, 2026, 10:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a3515ef21dc8190a720da87ed78dd1f completed June 19, 2026, 10:11 a.m.
NEDg Description generation batch_6a3516b1daa08190a21764ce7125ec69 completed June 19, 2026, 10:15 a.m.
NED2 Entity disambiguation (via description) batch_6a35172e773881908a625df198825ef0 completed June 19, 2026, 10:17 a.m.
Created at: April 10, 2026, 1:30 p.m.