Triple
T29698211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beijing area |
E751409
|
entity |
| Predicate | includesKeySite |
P5003
|
FINISHED |
| Object | Forbidden City |
—
|
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: Forbidden City | Statement: [Beijing area, includesKeySite, Forbidden City]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesKeySite Context triple: [Beijing area, includesKeySite, Forbidden City]
-
A.
isKeySiteOf
Indicates that a location serves as an important or central place for a particular event, activity, process, or function.
-
B.
containsSite
chosen
Indicates that one entity spatially or structurally includes another entity as a site or location within its bounds.
-
C.
isTypeSiteOf
Indicates that a site serves as the specific location or setting where a particular type, category, or classification is realized or occurs.
-
D.
isSiteOf
Indicates that a location or place serves as the setting or host for a particular event, activity, or feature.
-
E.
keyExecutionSite
Indicates the location or context in which a key (e.g., cryptographic or access key) is actually used or executed.
- 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_69f0d6266f8481909e70bb41cda18587 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fff4530f908190afe9387f732c2b7e |
completed | May 10, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fff3c01a64819091196875b0c88607 |
completed | May 10, 2026, 2:56 a.m. |
Created at: April 28, 2026, 7:22 p.m.