Triple
T27422106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harar Jugol city wall system |
E693070
|
entity |
| Predicate | isEnclosureOf |
P15848
|
FINISHED |
| Object | historic core of Harar Jugol |
—
|
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: historic core of Harar Jugol | Statement: [Harar Jugol city wall system, isEnclosureOf, historic core of Harar Jugol]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isEnclosureOf Context triple: [Harar Jugol city wall system, isEnclosureOf, historic core of Harar Jugol]
-
A.
isSubsegmentOf
Indicates that one segment is entirely contained within and forms a continuous part of another, larger segment.
-
B.
hasEnclosures
chosen
Indicates that an entity possesses or contains one or more enclosing structures, spaces, or bounded areas associated with it.
-
C.
isSubNeighborhoodOf
Indicates that one neighborhood is a smaller, contained part of another, larger neighborhood.
-
D.
isParentOf
Indicates that one entity is the biological or legal parent of another entity.
-
E.
isSubnetworkOf
Indicates that one network is a contained, subordinate, or component part of another, larger network.
- 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_69ef5208617081908f731d312e0fd1bc |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f62d1dcfa8819080a8b0dd701d69af |
completed | May 2, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 12:36 p.m.