Triple
T19100191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pern |
E467510
|
entity |
| Predicate | primaryDefenseAgainstThread |
P11967
|
FINISHED |
| Object | dragons and riders |
—
|
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: dragons and riders | Statement: [Pern, primaryDefenseAgainstThread, dragons and riders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryDefenseAgainstThread Context triple: [Pern, primaryDefenseAgainstThread, dragons and riders]
-
A.
coreProtection
Indicates that an entity provides essential safeguarding or defense for another entity’s central or most critical component.
-
B.
defensiveTask
chosen
Indicates a task in which an entity protects, guards, or defends another entity or resource from potential threats or harm.
-
C.
defenseLayer
Indicates a protective barrier or mechanism that shields an entity from harm, attack, or unwanted influence.
-
D.
defenseControl
Indicates that one entity exercises authority over, manages, or directs the defensive capabilities or protective measures of another entity.
-
E.
defends
Indicates that one entity protects or supports another entity against attack, criticism, or harm.
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e36d279081908aeb472cd740c302 |
completed | April 20, 2026, 8:27 a.m. |
| PD | Predicate disambiguation | batch_69e4b9ac41848190afd0f33b42cebe99 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:04 p.m.