Triple
T30518704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | trung tâm nghiên cứu lịch sử và bảo tồn di sản |
E776634
|
entity |
| Predicate | hoạtĐộngTại |
P81
|
FINISHED |
| Object | Việt Nam |
—
|
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: Việt Nam | Statement: [trung tâm nghiên cứu lịch sử và bảo tồn di sản, hoạtĐộngTại, Việt Nam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hoạtĐộngTại Context triple: [trung tâm nghiên cứu lịch sử và bảo tồn di sản, hoạtĐộngTại, Việt Nam]
-
A.
activity
chosen
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
-
B.
coordinatesActivitiesOf
Indicates that one entity organizes, aligns, or manages the activities of another entity or group of entities so they work together effectively.
-
C.
activityType
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
-
D.
otherActivity
Indicates that an entity is engaged in an activity that is different from a primary, specified, or expected activity.
-
E.
hostsActivitiesOf
Indicates that one entity provides the venue, context, or platform in which the activities of another entity take place.
- 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_69f2249b23c4819087fa85496d92f43f |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6880865d88190b3eeaf9478d4d6bd |
completed | May 2, 2026, 11:26 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:16 p.m.