Triple
T4145890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hibernia statue |
E89380
|
entity |
| Predicate | crowns |
P2300
|
FINISHED |
| Object | pediment of the General Post Office, Dublin |
—
|
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: pediment of the General Post Office, Dublin | Statement: [Hibernia statue, crowns, pediment of the General Post Office, Dublin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crowns Context triple: [Hibernia statue, crowns, pediment of the General Post Office, Dublin]
-
A.
crownType
Indicates the specific style or form of a crown associated with an entity.
-
B.
crownedWith
chosen
Indicates that one entity serves as a crown, top, or decorative upper covering placed upon another entity.
-
C.
hasCrownCount
Indicates the number of crowns that an entity possesses or is associated with.
-
D.
separateCrown
Indicates that one entity removes or detaches a crown from another entity.
-
E.
crownedBy
Indicates that an entity is formally invested with a rank, title, or authority through a crowning ceremony performed by another entity.
- 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_69aed95785788190ae75bcf0cd1cafdf |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af033ef6648190adde17f943d89c78 |
completed | March 9, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69af018c101081909070da5b11e5eb3d |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:43 p.m.