Triple
T8527183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Jakarta |
E201845
|
entity |
| Predicate | containsAttraction |
P5121
|
FINISHED |
| Object | Sea World Ancol |
E741876
|
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: Sea World Ancol | Statement: [North Jakarta, containsAttraction, Sea World Ancol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sea World Ancol Context triple: [North Jakarta, containsAttraction, Sea World Ancol]
-
A.
Ancol Dreamland
chosen
Ancol Dreamland is a large seaside resort and entertainment complex in Jakarta featuring theme parks, beaches, and various recreational facilities.
-
B.
Sea World
Sea World is a marine-themed amusement park and oceanarium on Australia's Gold Coast, known for its marine animal exhibits, shows, and rides.
-
C.
Siam Park
Siam Park is a large Thai-themed water park in Costa Adeje, Tenerife, renowned for its elaborate slides, wave pool, and lush tropical setting.
-
D.
Chimelong Ocean Kingdom
Chimelong Ocean Kingdom is a large marine-themed amusement park and aquarium complex in Zhuhai, China, known for its massive ocean habitats, animal shows, and thrill rides.
-
E.
Dolphinarium
A dolphinarium is a specialized marine facility where dolphins are kept, trained, and displayed for public shows, education, and research.
- 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_69ca83228b24819085d22e7dc99f5d94 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6477100819081fa20cb6b8ea3d7 |
completed | March 31, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce88f750cc819093c8902b2c285153 |
completed | April 2, 2026, 3:19 p.m. |
Created at: March 30, 2026, 6:16 p.m.