Triple
T28673152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Talent Manx |
E725782
|
entity |
| Predicate | ageEffect |
P165206
|
FINISHED |
| Object | grows younger by feeding on children |
—
|
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: grows younger by feeding on children | Statement: [Charles Talent Manx, ageEffect, grows younger by feeding on children]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageEffect Context triple: [Charles Talent Manx, ageEffect, grows younger by feeding on children]
-
A.
agedStyle
Indicates a relationship where something has a particular age-related style, appearance, or aesthetic (e.g., old-fashioned, vintage, or time-worn).
-
B.
ageSetting
Indicates that one entity specifies, adjusts, or defines the age value or age-related parameter of another entity.
-
C.
ageModel
Indicates a relationship where one entity specifies or provides the age of another entity, typically in terms of a particular age value or age-related classification.
-
D.
ageProgression
Indicates a temporal relationship where an entity’s age increases or advances over time.
-
E.
ageContext
Indicates the temporal or life-stage context in which an entity’s age is specified or interpreted.
- 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_69f01d85be388190b669a0e401e2f2c4 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f65705a3048190a3728b695ba2ae65 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651ac855481908e30c3b345d31356 |
completed | May 2, 2026, 7:34 p.m. |
| PDg | Predicate description generation | batch_69f6562ef4e4819082ce6abd41b74dc5 |
completed | May 2, 2026, 7:53 p.m. |
Created at: April 28, 2026, 5:05 a.m.