Triple
T19408907
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Munjeongjeon Hall |
E485536
|
entity |
| Predicate | functionWithinPalace |
P134693
|
FINISHED |
| Object | principal audience hall |
—
|
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: principal audience hall | Statement: [Munjeongjeon Hall, functionWithinPalace, principal audience hall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: functionWithinPalace Context triple: [Munjeongjeon Hall, functionWithinPalace, principal audience hall]
-
A.
functionRelativeToPalace
chosen
Indicates that an entity has a role, purpose, or operational function defined in relation to a specific palace.
-
B.
locatedInPalaceSection
Indicates that one entity is situated within a specific section or area of a palace.
-
C.
positionWithinCastle
Indicates that one entity is located inside the spatial boundaries of a castle.
-
D.
associatedWithPalace
Indicates a relationship where an entity has a connection, link, or involvement with a palace, such as through location, function, ownership, or affiliation.
-
E.
positionWithinForbiddenCity
Indicates that an entity’s location lies inside the spatial boundaries of the Forbidden City.
- 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e62af331108190b6b25ef8f386826e |
completed | April 20, 2026, 1:32 p.m. |
| PD | Predicate disambiguation | batch_69e4fd68b1f881908d273de1fee81a75 |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:37 p.m.