Triple
T2019642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shadharwan |
E44074
|
entity |
| Predicate | notCoveredBy |
P10124
|
FINISHED |
| Object | Kiswah lower edge (in some sections) |
—
|
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: Kiswah lower edge (in some sections) | Statement: [Shadharwan, notCoveredBy, Kiswah lower edge (in some sections)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notCoveredBy Context triple: [Shadharwan, notCoveredBy, Kiswah lower edge (in some sections)]
-
A.
doesNotCover
chosen
Indicates that one entity fails to include, protect, or extend over another entity or area.
-
B.
isCoveredBy
Indicates that one entity is physically or conceptually overlaid, protected, or enclosed by another entity.
-
C.
notClosedUnder
Indicates that applying the operation or relation to elements of a set can produce results that do not belong to that set, so the set is not closed under that operation or relation.
-
D.
notObservedIn
Indicates that a particular entity, event, or property has not been detected, recorded, or seen within a specified context, dataset, or environment.
-
E.
notGuaranteed
Indicates that the specified outcome, condition, or obligation is not assured to occur or be fulfilled.
- 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_69a8891201bc8190aca837be6de41579 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb8cfa5c88190b55bce5db968665b |
completed | March 7, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_69abb7a389408190a84a54856352f15b |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:38 p.m.