Triple
T23735278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Père David's deer |
E586523
|
entity |
| Predicate | originalCaptiveSource |
P87048
|
FINISHED |
| Object | European zoos |
—
|
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: European zoos | Statement: [Père David's deer, originalCaptiveSource, European zoos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalCaptiveSource Context triple: [Père David's deer, originalCaptiveSource, European zoos]
-
A.
capturedFrom
Indicates that one entity has taken possession or control of another entity away from a specified source or previous holder.
-
B.
originSite
chosen
Indicates the place or site from which something or someone originally comes or is derived.
-
C.
registrationOrigin
Indicates the source or context from which a registration event was initiated or created.
-
D.
mainSourceType
Indicates the primary category or kind of source from which something originates or is derived.
-
E.
originalWebsite
Indicates that one entity is the original or primary website from which another entity (such as a copy, mirror, or derivative site) is derived.
- 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_69e24907dc9c8190be074c9c96a0ec2d |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1bad07bd08190b04d7a4c8732a856 |
completed | April 29, 2026, 8:01 a.m. |
| PD | Predicate disambiguation | batch_69f155f012808190a4b1cbc155558ade |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:10 p.m.