Triple
T4360702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morrison shelter |
E98652
|
entity |
| Predicate | storedUnder |
P10157
|
FINISHED |
| Object | ground-floor ceiling |
—
|
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: ground-floor ceiling | Statement: [Morrison shelter, storedUnder, ground-floor ceiling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: storedUnder Context triple: [Morrison shelter, storedUnder, ground-floor ceiling]
-
A.
storeType
Indicates the category or kind of store associated with an entity, such as its retail or service type.
-
B.
storageFacility
Indicates a relationship where one entity serves as a place or facility used to store another entity or its items.
-
C.
locatedUnder
chosen
Indicates that one entity is positioned directly or generally beneath another entity in space.
-
D.
storesConfigurationFor
Indicates that one entity holds or maintains configuration settings that are used by or apply to another entity.
-
E.
storageOption
Indicates how or where something is stored, specifying the chosen method, medium, or configuration for its storage.
- 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_69b3454c772081908e20173e379e8ebe |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b351e3220881909dc9d02ab024abf5 |
completed | March 12, 2026, 11:53 p.m. |
| PD | Predicate disambiguation | batch_69b34f53e3cc8190bf5d4dbe2413bf65 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:16 p.m.