Triple
T18571827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sri Temasek |
E453891
|
entity |
| Predicate | relatedBuilding |
P3158
|
FINISHED |
| Object | Istana |
—
|
NE NERFINISHED |
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: Istana | Statement: [Sri Temasek, relatedBuilding, Istana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Istana Context triple: [Sri Temasek, relatedBuilding, Istana]
-
A.
The Istana
chosen
The Istana is the official presidential palace and primary ceremonial venue of Singapore, serving as the office and residence of the President.
-
B.
Istana Besar
Istana Besar is a grand royal palace in Johor Bahru that historically served as the main residence of the Sultan of Johor and a symbol of the state's monarchy.
-
C.
Istana Arau
Istana Arau is the royal palace and official residence of the Raja of Perlis in the town of Arau, Malaysia.
-
D.
Istana Mestika
Istana Mestika is a royal palace in Selangor, Malaysia, serving as one of the official homes of the state's ruling sultan.
-
E.
Istana Maziah
Istana Maziah is a historic royal palace in Kuala Terengganu, Malaysia, serving as the ceremonial and official seat of the Sultan of Terengganu.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53b021ea4819095fe06be88e74133 |
completed | April 19, 2026, 8:28 p.m. |
Created at: April 10, 2026, 11:43 a.m.