Triple
T34640768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brown Lands |
E889546
|
entity |
| Predicate | travelRouteFor |
P79601
|
FINISHED |
| Object | Fellowship’s journey down the Anduin |
—
|
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: Fellowship’s journey down the Anduin | Statement: [Brown Lands, travelRouteFor, Fellowship’s journey down the Anduin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: travelRouteFor Context triple: [Brown Lands, travelRouteFor, Fellowship’s journey down the Anduin]
-
A.
travelRouteOf
chosen
Indicates the path or itinerary that an entity follows or uses when traveling from one location to another.
-
B.
travelRouteContext
Indicates the contextual details (such as purpose, conditions, or circumstances) under which a particular travel route is taken or defined.
-
C.
journeyDestination
Indicates that one entity serves as the endpoint or intended destination of another entity’s journey or travel.
-
D.
travelsFor
Indicates that one entity moves from place to place on behalf of, or for the benefit or purpose of, another entity or objective.
-
E.
popularRouteVia
Indicates that a route between two locations commonly or frequently passes through a specified intermediate point or path.
- 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_69f349d724848190b63ad3407e0006d9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f73b731ec881908f3e4d5e97d31908 |
completed | May 3, 2026, 12:11 p.m. |
| PD | Predicate disambiguation | batch_69f73a3a5d008190971cbde33409682b |
completed | May 3, 2026, 12:06 p.m. |
Created at: May 1, 2026, 2:04 a.m.