Triple
T19760958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack Rabbit |
E474625
|
entity |
| Predicate | terrainUsage |
P83050
|
FINISHED |
| Object | ravine-hugging design |
—
|
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: ravine-hugging design | Statement: [Jack Rabbit, terrainUsage, ravine-hugging design]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terrainUsage Context triple: [Jack Rabbit, terrainUsage, ravine-hugging design]
-
A.
terrainIncludes
Indicates that a specified terrain area contains or encompasses another geographic or environmental feature within its boundaries.
-
B.
territorialUse
Indicates the use, control, or occupation of a geographic area or territory by an entity.
-
C.
tourUsage
Indicates how a tour is intended to be used or the manner in which it is utilized within a given context.
-
D.
terrainSpecialization
chosen
Indicates a relationship where an entity is particularly adapted or optimized for operation, performance, or use within a specific type of terrain.
-
E.
terminusAreaUse
Indicates how the area of a terminus (such as a station or endpoint facility) is utilized or functionally designated.
- 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6531f38b48190b1663870a8da5a59 |
completed | April 20, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69e5305016e08190b9561a96baecb0b8 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:48 p.m.