Triple
T16291188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 関東州 |
E395524
|
entity |
| Predicate | 関連港湾 |
P115895
|
FINISHED |
| Object | 旅順港 |
E718025
|
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: 旅順港 | Statement: [関東州, 関連港湾, 旅順港]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 旅順港 Context triple: [関東州, 関連港湾, 旅順港]
-
A.
Lüshun (Port Arthur)
chosen
Lüshun (Port Arthur) is a strategically important port town at the southern tip of the Liaodong Peninsula in northeastern China, historically known for its role in the First Sino-Japanese and Russo-Japanese Wars.
-
B.
Kaiping
Kaiping is a county-level city in Guangdong Province, China, known for its distinctive diaolou watchtowers and as part of the Sze Yup region with a strong overseas Chinese heritage.
-
C.
Port of Kaohsiung
The Port of Kaohsiung is Taiwan’s largest and busiest seaport, serving as a major international hub for container shipping and maritime trade in East Asia.
-
D.
Keelung
Keelung is a major port city in northeastern Taiwan known for its busy harbor, seafood markets, and coastal scenery.
-
E.
Shidao
Shidao is a small island in the South China Sea that forms part of the Amphitrite Group within the disputed Paracel Islands archipelago.
- 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_69d87f22c7248190a54c949738441e2e |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2491821d0819086cffdd7551ba85a |
completed | April 17, 2026, 2:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0025fd56008190a9cb896e7ea2d26a |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:05 a.m.