Triple
T20345652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gringai |
E495860
|
entity |
| Predicate | hasTraditionalDwelling |
P35447
|
FINISHED |
| Object | bark shelters |
—
|
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: bark shelters | Statement: [Gringai, hasTraditionalDwelling, bark shelters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTraditionalDwelling Context triple: [Gringai, hasTraditionalDwelling, bark shelters]
-
A.
hasTraditionalHouseStyle
Indicates that an entity possesses or is characterized by a traditional style of house or residential architecture.
-
B.
traditionallyHouses
chosen
Indicates that one entity has historically or customarily served as the location or container for another entity.
-
C.
hasTraditionalSettlementType
Indicates that an entity is associated with a specific traditional or historically established type of human settlement (e.g., village, town, hamlet).
-
D.
traditionallyBuiltOver
Indicates that one entity has been constructed on top of another in a manner consistent with long-established or customary building practices.
-
E.
hasHousingArrangement
Indicates that an entity has a specific type or status of housing or living arrangement in relation to another entity or context.
- 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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67838744481909069b76b25dd4bb9 |
completed | April 20, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_69e57636b4808190bc2855af48a3ccdc |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:24 a.m.