Triple
T5982946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Government Palace of Mongolia |
E133160
|
entity |
| Predicate | hasCeremonialArea |
P128
|
FINISHED |
| Object | front plaza on Sükhbaatar Square |
—
|
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: front plaza on Sükhbaatar Square | Statement: [Government Palace of Mongolia, hasCeremonialArea, front plaza on Sükhbaatar Square]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCeremonialArea Context triple: [Government Palace of Mongolia, hasCeremonialArea, front plaza on Sükhbaatar Square]
-
A.
ceremonialRegion
Indicates a region that is designated or used for ceremonial or ritual activities in relation to another entity.
-
B.
isCeremonial
Indicates that something is associated with, intended for, or used in a formal ceremony or ritual rather than for ordinary or practical purposes.
-
C.
ceremonyLocation
chosen
Indicates the place where a ceremony is held or takes place.
-
D.
ceremonialVenueFunction
Indicates that a venue serves a role or purpose specifically related to hosting or supporting ceremonial events or activities.
-
E.
ceremonyHeld
Indicates that a formal ceremony or ritual event has taken place at a particular time and/or location.
- 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_69c0086f45e8819098f73dd16d45ec9d |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04a6a9f2c8190b900cd7e3ab9fe42 |
completed | March 22, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69c049de98648190962b14fd341c93da |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:04 p.m.