Triple
T439464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South China Sea |
E10082
|
entity |
| Predicate | connectedTo |
P37
|
FINISHED |
| Object | Java Sea |
E23517
|
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: Java Sea | Statement: [South China Sea, connectedTo, Java Sea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Java Sea Context triple: [South China Sea, connectedTo, Java Sea]
-
A.
Java Sea
chosen
The Java Sea is a shallow, tropical marginal sea in Indonesia, lying between the islands of Java and Borneo and known for its busy shipping routes and rich marine biodiversity.
-
B.
SEAS
SEAS is the acronym for Yale University's School of Engineering & Applied Science, which houses its engineering and applied science programs.
-
C.
WaterWorld: A Live Sea War Spectacular
WaterWorld: A Live Sea War Spectacular is a high-octane stunt show themed around the post-apocalyptic Waterworld film, featuring pyrotechnics, jet-ski chases, and large-scale water effects.
-
D.
Wild Reef
Wild Reef is a major Shedd Aquarium exhibit that recreates a vibrant coral reef ecosystem, featuring sharks, rays, and diverse tropical marine life.
-
E.
Bluewater
Bluewater is a large out-of-town shopping and leisure centre located in Kent, England.
- 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_69a2e8465ef481909655c681b01e2986 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2ef2977888190a0590b2c1bd2f5da |
completed | Feb. 28, 2026, 1:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a4366eb0588190beb5c43828f8ca45 |
completed | March 1, 2026, 12:51 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.