Triple
T37369213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Mark of Rohan (northern side) |
E927791
|
entity |
| Predicate | hasDirectionWithinRohan |
P117258
|
FINISHED |
| Object | northern |
—
|
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: northern | Statement: [the Mark of Rohan (northern side), hasDirectionWithinRohan, northern]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectionWithinRohan Context triple: [the Mark of Rohan (northern side), hasDirectionWithinRohan, northern]
-
A.
containsDirectionOf
Indicates that one entity includes or encompasses the directional orientation or path associated with another entity.
-
B.
hasRouteDirection
Indicates that a specified route is associated with a particular travel direction (e.g., inbound, outbound, northbound).
-
C.
isDirection
Indicates that one entity specifies or represents the orientation or course along which another entity moves, points, or is aligned.
-
D.
hasDirectionInName
chosen
Indicates that the entity’s name explicitly contains a directional term (e.g., north, south, east, west, or similar).
-
E.
directionalRole
Indicates a role or function defined in terms of a direction or orientation relative to another entity or reference frame.
- 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_69f76eb820248190a5c395ca50ad002a |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff8ba3f8248190bbdf8e7ec2b35093 |
completed | May 9, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69ff8b41ba988190a7332e8317d10f09 |
completed | May 9, 2026, 7:30 p.m. |
Created at: May 3, 2026, 4:16 p.m.