Triple
T10403946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barzakh as-Suways |
E245214
|
entity |
| Predicate | hasApproximateWidthAtNarrowestPoint |
P13004
|
FINISHED |
| Object | about 120 kilometers |
—
|
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: about 120 kilometers | Statement: [Barzakh as-Suways, hasApproximateWidthAtNarrowestPoint, about 120 kilometers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateWidthAtNarrowestPoint Context triple: [Barzakh as-Suways, hasApproximateWidthAtNarrowestPoint, about 120 kilometers]
-
A.
isNarrowestPartOf
Indicates that one entity constitutes the slimmest or most constricted section within the extent or structure of another entity.
-
B.
hasApproximateMaximumWidth
chosen
Indicates that an entity’s maximum width is known only approximately, rather than as an exact value.
-
C.
isNarrow
Indicates that something has a small width or limited breadth relative to a reference or context.
-
D.
hasMinorAxisLength
Indicates the length of the shorter (minor) axis of an ellipse or elliptical shape associated with an entity.
-
E.
hasMaximumBreadth
Indicates that an entity possesses the greatest breadth (widest extent) among a set of comparable entities or within a defined 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_69d381be340c8190b05998703d42d224 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9e5fb58819081d7d3e1dc625197 |
completed | April 7, 2026, 11:26 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb438c481908dff87c47de2f069 |
completed | April 7, 2026, 10:43 a.m. |
Created at: April 6, 2026, 12:08 p.m.