Triple
T17096098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sesriem Canyon |
E414854
|
entity |
| Predicate | widthCharacteristic |
P619
|
FINISHED |
| Object | narrow |
—
|
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: narrow | Statement: [Sesriem Canyon, widthCharacteristic, narrow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: widthCharacteristic Context triple: [Sesriem Canyon, widthCharacteristic, narrow]
-
A.
width
chosen
Indicates the measurement of how wide an entity is, typically the extent of its horizontal dimension from side to side.
-
B.
spanCharacteristic
Indicates that one entity has a particular measurable or descriptive property that characterizes the extent, duration, or range of another entity or phenomenon.
-
C.
widthInColumns
Indicates the number of column units that an element or item spans within a grid or layout.
-
D.
codeCharacteristic
Indicates that one piece of code possesses a specific property, feature, or quality in relation to another referenced aspect.
-
E.
typicalWidth
Indicates the usual or characteristic width associated with an entity, as opposed to an exact or measured width in a specific instance.
- 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_69d886cfc8e88190b05ba466edd35591 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbfdc9c88190b4e75bbdf4105c1e |
completed | April 18, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69e35d67b14481909fcdbdeaa5c34785 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:35 a.m.