Triple
T1764782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hoàn Kiếm Lake |
E38736
|
entity |
| Predicate | isPublicSpace |
P27492
|
FINISHED |
| Object | true |
—
|
LITERAL 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: true | Statement: [Hoàn Kiếm Lake, isPublicSpace, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPublicSpace Context triple: [Hoàn Kiếm Lake, isPublicSpace, true]
-
A.
isInPublicSpace
chosen
Indicates that an entity is located within a space that is publicly accessible or open to the general public.
-
B.
isPublicBuilding
Indicates that a building is designated for public use, access, or service rather than being privately owned or restricted.
-
C.
isGreenSpaceFor
Indicates that one entity serves as a designated green or open space intended for use or benefit by another entity.
-
D.
isPublicEvent
Indicates that an event is open and accessible to the general public rather than restricted to a private or limited audience.
-
E.
isPublicMuseum
Indicates that an institution operates as a museum that is open and accessible to the general public, typically under public or non-profit ownership or management.
- F. None of above.
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_69a8862d562481908d7025a1c1f67c0d |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab173936b4819097332ee185996bbd |
completed | March 6, 2026, 6:04 p.m. |
| PD | Predicate disambiguation | batch_69aa61c9e06c819085489e00cfe72153 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:31 p.m.