Triple
T11886988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hiroshima–Kure Road |
E282809
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Hiroshima |
E29708
|
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: Hiroshima | Statement: [Hiroshima–Kure Road, connects, Hiroshima]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hiroshima Context triple: [Hiroshima–Kure Road, connects, Hiroshima]
-
A.
Hiroshima
chosen
Hiroshima is a Japanese city on Honshu Island internationally known as the first place in history to be devastated by an atomic bomb during World War II.
-
B.
Nagasaki
Nagasaki is a major port city in southwestern Japan historically known as one of the two cities devastated by an American atomic bomb during World War II.
-
C.
Kitahiroshima
Kitahiroshima is a city in Hokkaido, Japan, located near Sapporo and known as a residential and commercial suburb within the Sapporo metropolitan area.
-
D.
Higashihiroshima
Higashihiroshima is a city in Hiroshima Prefecture, Japan, known as an academic hub and regional center that hosts major institutions such as Hiroshima University.
-
E.
Daigo
Daigo was the era name (nengō) in Japanese history corresponding to the reign of Emperor Daigo in the early 10th century.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6ab2a90b08190a4e818821cc93e6d |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8d3a13370819086386fecb99e4f0b |
completed | April 10, 2026, 10:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f281fc9660819081fc2fd1f44440d8 |
completed | April 29, 2026, 10:11 p.m. |
Created at: April 8, 2026, 9:44 p.m.