Triple
T33886907
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arab-Berber civilization |
E868654
|
entity |
| Predicate | urbanCentersInclude |
P158407
|
FINISHED |
| Object | Fez |
—
|
NE NERFINISHED |
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: Fez | Statement: [Arab-Berber civilization, urbanCentersInclude, Fez]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: urbanCentersInclude Context triple: [Arab-Berber civilization, urbanCentersInclude, Fez]
-
A.
urbanCentersCount
Indicates the number of urban centers associated with or contained within a given entity.
-
B.
urbanCenterServed
Indicates that a particular urban center is provided with services or coverage by a specified entity (such as an infrastructure system, facility, or organization).
-
C.
notableCityCenter
Indicates that a location serves as a prominent or significant central area within a city.
-
D.
urbanCenterDevelopedInto
Indicates that an urban center transformed or evolved over time into another, more developed or differently structured urban center.
-
E.
hasCentralCities
chosen
Indicates that an entity is associated with one or more cities that serve as its primary or central urban locations.
- 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_69f34996761c8190864e42f7c9cf215b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7051ad6e4819095e82bbd64761803 |
completed | May 3, 2026, 8:19 a.m. |
| PD | Predicate disambiguation | batch_69f700fe24e08190998e2c96fbaaad38 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:48 a.m.