Triple
T9777819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Narya |
E237289
|
entity |
| Predicate | notTouchedBy |
P90610
|
FINISHED |
| Object | Sauron during forging |
—
|
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: Sauron during forging | Statement: [Narya, notTouchedBy, Sauron during forging]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notTouchedBy Context triple: [Narya, notTouchedBy, Sauron during forging]
-
A.
notUsedAt
Indicates that a particular entity is not utilized, applied, or active at a specified location, time, or context.
-
B.
notHeldIn
Indicates that an event, activity, or state does not take place or is not located within a specified context, location, or time frame.
-
C.
notObservedBy
Indicates that an entity, event, or condition is not detected, recorded, or perceived by a specified observer or observation process.
-
D.
notAbout
Indicates that a given entity, statement, or resource does not concern, reference, or pertain to another specified entity or topic.
-
E.
notCleanedFor
Indicates that one entity has not been cleaned, maintained, or cleared in preparation for use by another entity.
- F. None of above. chosen
Provenance (4 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_69ca84d975a08190aab25b02a89bdab3 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda13545808190a47544b0cc666e20 |
completed | April 1, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69cd03d77c6c81909b675955bf113320 |
completed | April 1, 2026, 11:39 a.m. |
| PDg | Predicate description generation | batch_69cd06aa8bc88190904be19c8953def8 |
completed | April 1, 2026, 11:51 a.m. |
Created at: March 30, 2026, 8:26 p.m.