Triple
T5110419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colonel Brandon |
E115199
|
entity |
| Predicate | ageRelativeToOtherCharacters |
P43008
|
FINISHED |
| Object | older than Edward Ferrars |
—
|
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: older than Edward Ferrars | Statement: [Colonel Brandon, ageRelativeToOtherCharacters, older than Edward Ferrars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageRelativeToOtherCharacters Context triple: [Colonel Brandon, ageRelativeToOtherCharacters, older than Edward Ferrars]
-
A.
relativeOfMainCharacter
Indicates that one entity is a family member or relative of the main character entity.
-
B.
ageInSeries
Indicates the age of an entity as it appears or is depicted within a specific series or installment of a work.
-
C.
timeRelativeToBirth
Indicates the temporal position of an event or state relative to an entity’s birth (e.g., before, at, or after birth).
-
D.
hasRelativeAge
chosen
Indicates that one entity has an age that is defined or compared in relation to the age of another entity.
-
E.
riftAge
Indicates the age or time since formation of a geological rift or rift-related feature.
- 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_69bd4441d1648190a54a533895041987 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75ad362c8190b9cbded390aaea3c |
completed | March 20, 2026, 4:28 p.m. |
| PD | Predicate disambiguation | batch_69bd715fe3a8819087d3065adddba515 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:41 p.m.