Triple
T37630451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rabat |
E936324
|
entity |
| Predicate | hasNearbyFortifiedCity |
P66389
|
FINISHED |
| Object | Mdina |
—
|
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: Mdina | Statement: [Rabat, hasNearbyFortifiedCity, Mdina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyFortifiedCity Context triple: [Rabat, hasNearbyFortifiedCity, Mdina]
-
A.
hasFortificationNearby
chosen
Indicates that one entity is located in proximity to, or within the immediate area of, a fortification structure associated with it.
-
B.
hasNearbyMilitaryTown
Indicates that one location is situated close to a town whose primary function or identity is associated with military presence or activity.
-
C.
isInFortifiedTown
Indicates that an entity is located within a town that is protected by defensive structures or fortifications.
-
D.
hasNearbyAncientCity
Indicates that one entity is located close to another entity that is classified as an ancient city.
-
E.
isFortifiedCity
Indicates that a city is strengthened with defensive structures or fortifications, such as walls, ramparts, or similar protective works.
- 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_69f76ed24820819081bafd36e9088701 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00ac5654a0819090701f61a5802d64 |
completed | May 10, 2026, 4:03 p.m. |
| PD | Predicate disambiguation | batch_6a00ab94b5e881909e15d1342e5f43be |
completed | May 10, 2026, 4 p.m. |
Created at: May 3, 2026, 4:18 p.m.