Triple
T27959966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Twenty-Four Histories |
E704552
|
entity |
| Predicate | hasApproximateTotalVolumeCount |
P2734
|
FINISHED |
| Object | over 3000 juan |
—
|
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: over 3000 juan | Statement: [Twenty-Four Histories, hasApproximateTotalVolumeCount, over 3000 juan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateTotalVolumeCount Context triple: [Twenty-Four Histories, hasApproximateTotalVolumeCount, over 3000 juan]
-
A.
approximateVolumeInCubicCentimetres
Indicates that one entity has an estimated or roughly calculated volume measured in cubic centimetres.
-
B.
numberOfVolumes
chosen
Indicates the total count of separate volumes or parts that make up a multi-volume work or collection.
-
C.
hasEstimatedOriginalVolume
Indicates that an entity is associated with an approximate or calculated value for its original volume.
-
D.
hasApproximateBrickCount
Indicates that an entity is associated with an estimated or non-exact number of bricks.
-
E.
hasApproximateVendorCount
Indicates that an entity is associated with an estimated or non-exact number of vendors.
- 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_69ef841061e48190b5570f9562f7434d |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f7431c0eec81909ead443e07d75e18 |
completed | May 3, 2026, 12:44 p.m. |
| PD | Predicate disambiguation | batch_69f74143cf708190a12d487884298437 |
completed | May 3, 2026, 12:36 p.m. |
Created at: April 27, 2026, 7:31 p.m.