Triple
T24306087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Region of al-Yamama |
E612538
|
entity |
| Predicate | capitalApproximateLocation |
P155503
|
FINISHED |
| Object | site of modern Riyadh |
—
|
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: site of modern Riyadh | Statement: [Region of al-Yamama, capitalApproximateLocation, site of modern Riyadh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalApproximateLocation Context triple: [Region of al-Yamama, capitalApproximateLocation, site of modern Riyadh]
-
A.
capitalPossiblyAt
Indicates a possible or uncertain capital relationship, where one location may be the capital of another but this is not definitively established.
-
B.
departmentCapitalOf
Indicates that a location serves as the administrative capital of a specified department (an administrative division).
-
C.
capitalLikeCity
Indicates that a capital city shares similar characteristics or status to a particular city.
-
D.
capitalRenamedFrom
Indicates that a capital city previously had a different name, specifying the former name from which it was renamed.
-
E.
isFinancialCapitalOf
Indicates that a city or region serves as the primary center for a country’s or area’s financial, banking, and economic market activities.
- F. None of above. chosen
Provenance (4 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_69e2d7d91bb48190bc5377d17a85fb21 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f292272af88190b9c23615adbac911 |
completed | April 29, 2026, 11:20 p.m. |
| PD | Predicate disambiguation | batch_69f1c45c6ec081908401b69424428100 |
completed | April 29, 2026, 8:42 a.m. |
| PDg | Predicate description generation | batch_69f1c6d4e99081909f61899eccafb73e |
completed | April 29, 2026, 8:52 a.m. |
Created at: April 18, 2026, 1:30 a.m.