Triple
T13207761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haruna |
E314408
|
entity |
| Predicate | sunkAt |
P3148
|
FINISHED |
| Object | Kure, Japan |
E48915
|
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: Kure, Japan | Statement: [Haruna, sunkAt, Kure, Japan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kure, Japan Context triple: [Haruna, sunkAt, Kure, Japan]
-
A.
Kure
Kure is a Japanese port city in Hiroshima Prefecture known historically as a major naval base and shipbuilding center.
-
B.
Kure, Hiroshima Prefecture, Japan
chosen
Kure, in Hiroshima Prefecture, Japan, is a historic port city renowned as a major naval base and shipbuilding center, particularly prominent during the early 20th century.
-
C.
Kariya, Japan
Kariya, Japan is an industrial city in Aichi Prefecture known as a manufacturing hub, particularly for the automotive industry, and as part of the Nagoya metropolitan area.
-
D.
Morioka, Japan
Morioka, Japan is a historic city in Iwate Prefecture on Japan’s main island of Honshu, known for its scenic mountain surroundings, traditional culture, and distinctive local noodle dishes.
-
E.
Tsuyama, Japan
Tsuyama, Japan is a historic city in Okayama Prefecture known for its well-preserved castle ruins, traditional townscape, and famous cherry blossom viewing spots.
- 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_69d806aee7308190b70a237ba2a6e3e1 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c9cb7ac819095cff8699993c419 |
completed | April 10, 2026, 11:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6f611b11c8190b9f89313eb2b5fab |
completed | May 3, 2026, 7:15 a.m. |
Created at: April 9, 2026, 9:17 p.m.