Triple
T2863817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miho Museum |
E63387
|
entity |
| Predicate | undergroundPortion |
P15152
|
FINISHED |
| Object | about 80 percent of the building is underground |
—
|
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: about 80 percent of the building is underground | Statement: [Miho Museum, undergroundPortion, about 80 percent of the building is underground]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: undergroundPortion Context triple: [Miho Museum, undergroundPortion, about 80 percent of the building is underground]
-
A.
undergroundBranch
Indicates that one entity is a branch or extension of another that operates or exists in a hidden, secret, or non-public manner.
-
B.
partOfTunnel
Indicates that one entity forms a physical segment or component within the structure or extent of a tunnel.
-
C.
hasUndergroundSection
chosen
Indicates that an entity includes a portion or segment that is located below ground level.
-
D.
undergroundAlternateCommandCenter
Indicates a facility serving as a backup or secondary command center that is located underground.
-
E.
hasUnderpass
Indicates that one location or structure includes or is connected by an underpass beneath another feature or pathway.
- 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_69ab4c41e8c08190a9e8f5249cc12610 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdfb853908190aa2fd492e9fa5e87 |
completed | March 7, 2026, 8:20 a.m. |
| PD | Predicate disambiguation | batch_69abdd123ec48190af50a1859aea50b7 |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:02 p.m.