Triple
T5877792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Himeji Castle |
E130668
|
entity |
| Predicate | numberOfStoriesMainKeep |
P995
|
FINISHED |
| Object | 5 external stories |
—
|
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: 5 external stories | Statement: [Himeji Castle, numberOfStoriesMainKeep, 5 external stories]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfStoriesMainKeep Context triple: [Himeji Castle, numberOfStoriesMainKeep, 5 external stories]
-
A.
numberOfStories
chosen
Indicates the total count of levels or floors that a structure or building has.
-
B.
numberOfMainTexts
Indicates the quantity of primary or main textual components associated with an entity.
-
C.
storyNumber
Indicates the numerical identifier assigned to a specific story within a collection, sequence, or dataset.
-
D.
talesCount
Indicates the number of tales associated with or attributed to a given entity.
-
E.
mainSeries
Indicates that one creative work is the primary or canonical series to which another related work (such as a spin-off, side story, or adaptation) belongs.
- 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_69c0085523688190bfd487479ce819e6 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0432fea5881909f5c291dd8db6105 |
completed | March 22, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69c033499ca08190bd26cee5b03f6306 |
completed | March 22, 2026, 6:22 p.m. |
Created at: March 22, 2026, 3:57 p.m.