Triple
T16937552
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kasbah of Tunis |
E410868
|
entity |
| Predicate | locationRelativeToMedina |
P35867
|
FINISHED |
| Object | western edge of the Medina of Tunis |
—
|
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: western edge of the Medina of Tunis | Statement: [Kasbah of Tunis, locationRelativeToMedina, western edge of the Medina of Tunis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationRelativeToMedina Context triple: [Kasbah of Tunis, locationRelativeToMedina, western edge of the Medina of Tunis]
-
A.
distanceFromMedinaCenterApprox
Indicates an approximate measure of how far something is located from the center of Medina.
-
B.
directionFromMedina
chosen
Indicates the geographic direction or bearing of one location as measured outward from Medina.
-
C.
positionRelativeToCaliph
Indicates the spatial or hierarchical position an entity holds in relation to the caliph.
-
D.
distanceFromKaaba
Indicates the spatial distance between an entity’s location and the Kaaba.
-
E.
positionOnKaaba
Indicates that one entity occupies a specific location or placement on the surface or structure of the Kaaba.
- 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_69d886c886688190967be07322597ac9 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cf2adf448190ab0dbebb3addbd80 |
completed | April 18, 2026, 6:36 p.m. |
| PD | Predicate disambiguation | batch_69e32b9aa8748190b248890aca86753d |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:30 a.m.