Triple
T13083096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zaydi Imamate in Yemen |
E310259
|
entity |
| Predicate | peakExtent |
P5049
|
FINISHED |
| Object | control over most of Yemen |
—
|
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: control over most of Yemen | Statement: [Zaydi Imamate in Yemen, peakExtent, control over most of Yemen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: peakExtent Context triple: [Zaydi Imamate in Yemen, peakExtent, control over most of Yemen]
-
A.
peakTerritorialExtentUnder
Indicates that one entity reached its greatest territorial size or coverage while under the control, rule, or influence of another entity.
-
B.
peakTerritorialExtent
chosen
Indicates the maximum geographic area or territorial size that an entity controlled or occupied at the height of its expansion.
-
C.
maximumExtent
Indicates the greatest or furthest degree, size, or range to which something can extend or apply within a given context.
-
D.
verticalExtent
Indicates the total height or vertical span of an entity or region from its lowest to highest point.
-
E.
peakSize
Indicates the magnitude or height of a peak within a given signal, distribution, or dataset.
- 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_69d806a733548190989cfd4ce981ca33 |
completed | April 9, 2026, 8:05 p.m. |
| NER | Named-entity recognition | batch_69d9811add9881908a92186dab5b6d48 |
completed | April 10, 2026, 11 p.m. |
| PD | Predicate disambiguation | batch_69d9803f6c508190bfadfbc2d00c2c64 |
completed | April 10, 2026, 10:57 p.m. |
Created at: April 9, 2026, 9:02 p.m.