Triple
T13903682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beijing Zoo |
E334290
|
entity |
| Predicate | hasAnimalCollectionSize |
P6210
|
FINISHED |
| Object | thousands of individual animals |
—
|
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: thousands of individual animals | Statement: [Beijing Zoo, hasAnimalCollectionSize, thousands of individual animals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAnimalCollectionSize Context triple: [Beijing Zoo, hasAnimalCollectionSize, thousands of individual animals]
-
A.
hasAnimalCollection
Indicates that one entity possesses or maintains a collection or group of animals associated with it.
-
B.
hasHerdSize
Indicates the number of individual animals that belong to a particular herd.
-
C.
collectionSize
Indicates the total number of items contained within a specified collection.
-
D.
numberOfAnimals
chosen
Indicates the quantity of animals associated with a given entity or context.
-
E.
hasAnimal
Indicates that one entity possesses, keeps, or is associated with an animal.
- 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de25db1e308190aaed6a21e443cc44 |
completed | April 14, 2026, 11:32 a.m. |
| PD | Predicate disambiguation | batch_69dd464b1ab48190ae50bfc902bf6ef7 |
completed | April 13, 2026, 7:38 p.m. |
Created at: April 9, 2026, 10:16 p.m.