Triple
T36821184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hispania Tarraconensis |
E909887
|
entity |
| Predicate | laterSubdividedInto |
P160867
|
FINISHED |
| Object | Gallaecia |
—
|
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: Gallaecia | Statement: [Hispania Tarraconensis, laterSubdividedInto, Gallaecia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterSubdividedInto Context triple: [Hispania Tarraconensis, laterSubdividedInto, Gallaecia]
-
A.
subdivisionsLater
Indicates that one entity represents a set of subdivisions or component parts that occur after, or are temporally or sequentially later than, those of another entity.
-
B.
subdivisionsLater
chosen
Indicates that one entity’s subdivisions occur after or at a later stage than the subdivisions of another entity.
-
C.
subdividedBy
Indicates that something is divided into smaller parts or sections by another entity or criterion.
-
D.
introducedSubdivision
Indicates that one entity created or formally established a new subdivision or sub-unit within another entity or structure.
-
E.
formerSubdivisionOf
Indicates that an entity once functioned as an administrative or territorial part of another entity but no longer holds that status.
- 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_69f76e7dd13c81908c60b05adb49eeb5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00be8ee4bc8190b795d9606f0e490c |
completed | May 10, 2026, 5:21 p.m. |
| PD | Predicate disambiguation | batch_6a00bde163c88190867104bd08cac2ee |
completed | May 10, 2026, 5:18 p.m. |
Created at: May 3, 2026, 4:13 p.m.