Triple
T36768875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treebeard |
E908419
|
entity |
| Predicate | keptUnderWatch |
P140431
|
FINISHED |
| Object | Saruman |
—
|
NE NERFINISHED |
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: Saruman | Statement: [Treebeard, keptUnderWatch, Saruman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keptUnderWatch Context triple: [Treebeard, keptUnderWatch, Saruman]
-
A.
يراقب
Indicates that one entity is watching, monitoring, or observing another entity or situation.
-
B.
monitoredFor
Indicates that one entity is being observed or tracked over time to detect, assess, or manage the occurrence or progression of another entity (such as a condition, event, or risk).
-
C.
keptIn
Indicates that one entity is stored, contained, or maintained inside another entity as its location or container.
-
D.
closelyWatched
chosen
Indicates that one entity is monitoring or observing another with particular attention and frequency, often to track behavior or changes closely.
-
E.
keptWith
Indicates that one entity is stored, maintained, or held together in association with another entity.
- 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_69f76e786ba481909cdcf6cf6b39dd32 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c9f5a8848190ba956ff27f44e396 |
completed | May 3, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.