Triple
T38449045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shagrat |
E906715
|
entity |
| Predicate | transportedItem |
P198365
|
FINISHED |
| Object | Mithril coat to Barad-dûr |
—
|
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: Mithril coat to Barad-dûr | Statement: [Shagrat, transportedItem, Mithril coat to Barad-dûr]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transportedItem Context triple: [Shagrat, transportedItem, Mithril coat to Barad-dûr]
-
A.
transportedObject
chosen
Indicates that an entity is the object being moved or carried from one location to another in a transport event.
-
B.
transportedIn
Indicates that one entity is carried or conveyed inside another entity as a means of transport.
-
C.
transportedWith
Indicates that one entity was moved or carried together with another entity as part of the same transport event.
-
D.
transportedAs
Indicates that one entity is moved or carried from one place to another in the form, role, or medium specified by another entity.
-
E.
transportedFor
Indicates that one entity was moved or carried from one place to another for the benefit, use, or purpose of another entity or activity.
- 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_69f76e72878c8190a692836c8b01b58b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffff262fac8190a26ed0577e1860bd |
completed | May 10, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69fffcad7d7c8190a4ad7bb35e33bb75 |
completed | May 10, 2026, 3:34 a.m. |
Created at: May 3, 2026, 4:31 p.m.