Triple
T4558842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman lictor |
E120544
|
entity |
| Predicate | clearedWayFor |
P29688
|
FINISHED |
| Object | magistrate |
—
|
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: magistrate | Statement: [Roman lictor, clearedWayFor, magistrate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clearedWayFor Context triple: [Roman lictor, clearedWayFor, magistrate]
-
A.
hasNavigationClearance
Indicates that an entity has been granted authorization to navigate through a specified area or along a particular route.
-
B.
navigationClearanceType
Indicates the specific type or category of clearance granted for a navigation-related operation or movement.
-
C.
hasRightOfWay
chosen
Indicates that one entity is entitled to proceed or act before another in a shared space or interaction, without having to yield.
-
D.
firstEntranceClearedBy
Indicates that the subject’s first entrance or initial access point was cleared, authorized, or made passable by the specified agent or process.
-
E.
clearanceBelow
Indicates that one entity is positioned at a lower vertical clearance level than another, typically with less space between it and an underlying reference surface.
- 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_69bd4636f1648190a701445c2fcd9c17 |
completed | March 20, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69bd5829cc34819086ad2ae58446502e |
completed | March 20, 2026, 2:22 p.m. |
| PD | Predicate disambiguation | batch_69bd52254c648190a5144cfe8fa7e409 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:09 p.m.