Triple
T15907216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bab Souika |
E385749
|
entity |
| Predicate | wallAssociation |
P43476
|
FINISHED |
| Object | part of former fortifications 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: part of former fortifications of Tunis | Statement: [Bab Souika, wallAssociation, part of former fortifications of Tunis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wallAssociation Context triple: [Bab Souika, wallAssociation, part of former fortifications of Tunis]
-
A.
wallFeature
chosen
Indicates that one entity functions as a structural or design feature associated with a wall of another entity.
-
B.
wallPlan
Indicates a planned or designed configuration of walls within a space or structure.
-
C.
hasWall
Indicates that one entity possesses, includes, or is bounded by a wall.
-
D.
antAssociation
Indicates a relationship in which one entity is associated or interacts in a specific, notable way with ants.
-
E.
wallMaterial
Indicates that one entity is the material from which a wall or walls of another entity are constructed.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142ca3b208190946c3aa4c1e6087c |
completed | April 16, 2026, 8:12 p.m. |
Created at: April 10, 2026, 4:52 a.m.