Triple
T11857025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hojo (abbot’s quarters) |
E282064
|
entity |
| Predicate | oftenAdjacentTo |
P44955
|
FINISHED |
| Object | temple garden |
—
|
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: temple garden | Statement: [Hojo (abbot’s quarters), oftenAdjacentTo, temple garden]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenAdjacentTo Context triple: [Hojo (abbot’s quarters), oftenAdjacentTo, temple garden]
-
A.
isAdjacentTo
Indicates that one entity is directly next to or bordering another without anything of the same type in between.
-
B.
locatedInOrAdjacentTo
Indicates that one entity is either situated within the boundaries of another entity or directly next to it, sharing a common border or edge.
-
C.
neighboringTo
Indicates that one entity is located directly adjacent or very close to another entity, sharing a common boundary or immediate vicinity.
-
D.
situatedNextTo
chosen
Indicates that one entity is located immediately beside another, with no significant separation between them.
-
E.
geographicallyAdjacentTo
Indicates that two geographic entities share a common boundary or are directly next to each other in space.
- 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a699089c8190b7a298baf13dcded |
completed | April 10, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69d8a2573dbc8190ab432e8e28fde6cc |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:43 p.m.