Triple
T1166708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaul |
E24814
|
entity |
| Predicate | partiallyCorrespondsTo |
P25442
|
FINISHED |
| Object | modern Belgium |
—
|
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: modern Belgium | Statement: [Gaul, partiallyCorrespondsTo, modern Belgium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partiallyCorrespondsTo Context triple: [Gaul, partiallyCorrespondsTo, modern Belgium]
-
A.
partlyDefinedBy
Indicates that one entity’s nature, role, or characteristics are only partially determined or specified by another entity.
-
B.
implementedInPartBy
Indicates that the realization or execution of something is partially carried out, supported, or fulfilled by the referenced entity.
-
C.
partiallySuccessor
Indicates that one entity follows another in a sequence or process, but only to a limited or incomplete extent rather than as a full or direct successor.
-
D.
partlyConcurrentWith
Indicates that two events or intervals overlap in time for some, but not all, of their durations.
-
E.
partlyProtectedBy
Indicates that an entity is only partially safeguarded or covered by a specified protective measure, not fully protected.
- F. None of above. chosen
Provenance (4 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_69a494082a7c819095004f423f294a64 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bccd75048190b8ce88237c1a748b |
completed | March 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69a4bb548c1481909092626c572d8782 |
completed | March 1, 2026, 10:19 p.m. |
| PDg | Predicate description generation | batch_69a4bc8ae87c81908ca5d94f63ad0e80 |
completed | March 1, 2026, 10:24 p.m. |
Created at: March 1, 2026, 7:45 p.m.