Triple
T33848380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SEPU |
E867543
|
entity |
| Predicate | hasPrefixRegion |
P147378
|
FINISHED |
| Object | SE |
—
|
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: SE | Statement: [SEPU, hasPrefixRegion, SE]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrefixRegion Context triple: [SEPU, hasPrefixRegion, SE]
-
A.
hasPrefix
Indicates that one entity occurs at the beginning of another entity, serving as its starting segment or initial substring.
-
B.
regionPrefix
chosen
Indicates that one region’s identifier or code serves as the starting substring (prefix) of another region’s identifier or code, expressing a hierarchical or nested regional relationship.
-
C.
hasRegionKey
Indicates that an entity is associated with a specific region through a unique identifying key.
-
D.
hasRegistryPrefix
Indicates that one entity serves as a registry namespace or prefix under which the other entity is registered or identified.
-
E.
hasEarlierStartInRegion
Indicates that one event or entity begins earlier in time than another within a specified geographic or logical 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_69f349937b648190a34ada70f6a2b534 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a01ed1790148190b08c1dba53de4371 |
completed | May 11, 2026, 2:52 p.m. |
| PD | Predicate disambiguation | batch_6a01e9c20798819085760b377dc7b3fa |
completed | May 11, 2026, 2:37 p.m. |
Created at: May 1, 2026, 1:47 a.m.