Triple
T1862644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Osaka Museum of History |
E34849
|
entity |
| Predicate | hasInteractiveFeature |
P182
|
FINISHED |
| Object | hands-on displays |
—
|
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: hands-on displays | Statement: [Osaka Museum of History, hasInteractiveFeature, hands-on displays]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInteractiveFeature Context triple: [Osaka Museum of History, hasInteractiveFeature, hands-on displays]
-
A.
hasInteractiveActivity
Indicates that an entity includes or is associated with an activity that requires active user participation or engagement.
-
B.
hasFeature
chosen
Indicates that an entity possesses, exhibits, or includes a particular characteristic, attribute, or component.
-
C.
hasInteraction
Indicates that there is some form of interaction or mutual action occurring between the related entities.
-
D.
hasBroadcastFeature
Indicates that an entity includes or supports a broadcast-related capability or functionality.
-
E.
hasTouchControls
Indicates that an entity supports or is operated through touch-based input controls.
- 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_69a88600b2f88190bc09303e68ab517e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abb16c09e48190a345c95eab59fd87 |
completed | March 7, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69abafe02c3c819093a4744b476106ca |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.