Triple
T30221151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | censor (Roman Republic) |
E768346
|
entity |
| Predicate | couldRemove |
P170756
|
FINISHED |
| Object | public horse from equites |
—
|
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: public horse from equites | Statement: [censor (Roman Republic), couldRemove, public horse from equites]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: couldRemove Context triple: [censor (Roman Republic), couldRemove, public horse from equites]
-
A.
mayRemove
Indicates that one entity is permitted or authorized to remove another entity or its association.
-
B.
canBeRemovedBy
Indicates that one entity is capable of eliminating, detaching, or undoing another entity or its effect.
-
C.
removal
Indicates the action or process by which something is taken away, eliminated, or detached from something else.
-
D.
removable
Indicates that one entity can be detached, taken off, or separated from another without causing damage or permanent alteration.
-
E.
couldBeDismissedBy
Indicates that one entity has the authority or power to terminate, remove, or discharge the other from a position, role, or obligation.
- 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_69f2247fd8b8819087fcf83cb7a05eb8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f695f9fe7c819084322bf6cdc70a13 |
completed | May 3, 2026, 12:25 a.m. |
| PD | Predicate disambiguation | batch_69f690ed5d008190831cf8e44cce28af |
completed | May 3, 2026, 12:03 a.m. |
| PDg | Predicate description generation | batch_69f695385a2881908cc28ef97fffc867 |
completed | May 3, 2026, 12:22 a.m. |
Created at: April 29, 2026, 7:35 p.m.