Triple
T33843912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingdom of Uvea |
E867425
|
entity |
| Predicate | hasNeighborTraditionalKingdom |
P112308
|
FINISHED |
| Object | Kingdom of Sigave |
—
|
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: Kingdom of Sigave | Statement: [Kingdom of Uvea, hasNeighborTraditionalKingdom, Kingdom of Sigave]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNeighborTraditionalKingdom Context triple: [Kingdom of Uvea, hasNeighborTraditionalKingdom, Kingdom of Sigave]
-
A.
hasNeighboringChiefdom
Indicates that one chiefdom is geographically adjacent to or directly borders another chiefdom.
-
B.
hasNeighboringRealm
Indicates that one realm is geographically adjacent to another, sharing a common boundary or border.
-
C.
hasViewOfKingdom
Indicates that an entity has a vantage point from which it can see or overlook a kingdom.
-
D.
hasNeighboringExclave
Indicates that one entity possesses an exclave that directly borders or is adjacent to an exclave of another entity.
-
E.
neighbouringKingdom
chosen
Indicates that one kingdom is directly adjacent to and shares a border with another kingdom.
- 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_69f349937b648190a34ada70f6a2b534 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff965f9be48190b015b788207be676 |
completed | May 9, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69ff95d3015c8190b9d293fe31b859c3 |
completed | May 9, 2026, 8:15 p.m. |
Created at: May 1, 2026, 1:47 a.m.