Triple
T26853509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pevensie siblings |
E676119
|
entity |
| Predicate | ruleFrom |
P91355
|
FINISHED |
| Object | Cair Paravel |
—
|
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: Cair Paravel | Statement: [Pevensie siblings, ruleFrom, Cair Paravel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ruleFrom Context triple: [Pevensie siblings, ruleFrom, Cair Paravel]
-
A.
rulesBy
chosen
Indicates that one entity governs, controls, or exercises authoritative power over another entity.
-
B.
usesRulesFrom
Indicates that one entity applies, follows, or is governed by the rules defined or provided by another entity.
-
C.
rulesOut
Indicates that the presence or truth of one entity, condition, or option excludes or makes another entity, condition, or option impossible or invalid.
-
D.
underRule
Indicates that one entity is governed, controlled, or subject to the authority, rules, or dominion of another entity.
-
E.
relatedRule
Indicates that one rule is connected or associated with another rule, typically through some logical, structural, or referential relationship.
- 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_69eee9b9d7708190a15d7485709ae981 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61b94b4a88190b24e8955029ec64e |
completed | May 2, 2026, 3:43 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:19 a.m.