Triple
T2204326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isthmus of Suez |
E50560
|
entity |
| Predicate | formsLandBoundaryBetween |
P224
|
FINISHED |
| Object | Egyptian mainland in Africa |
—
|
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: Egyptian mainland in Africa | Statement: [Isthmus of Suez, formsLandBoundaryBetween, Egyptian mainland in Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsLandBoundaryBetween Context triple: [Isthmus of Suez, formsLandBoundaryBetween, Egyptian mainland in Africa]
-
A.
borderedBy
chosen
Indicates that one entity shares a common boundary or edge with another entity.
-
B.
provinceBordering
Indicates that two provinces share a common boundary or border with each other.
-
C.
connectsCountryBorder
Indicates that one entity forms a direct land or maritime border connection with a specified country.
-
D.
countryBordering
Indicates that one country shares a land or maritime boundary directly with another country.
-
E.
borderRegionOf
Indicates that one region lies along, touches, or forms part of the boundary of another region.
- 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_69a88b044ab48190add007487680f009 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc1baa0948190b07ffc347a4f714e |
completed | March 7, 2026, 6:12 a.m. |
| PD | Predicate disambiguation | batch_69abbda8a6dc8190aa855ce2d17194b1 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:46 p.m.