Triple
T33911416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anni-Frid Lyngstad |
E869323
|
entity |
| Predicate | upbringingGuardian |
P8768
|
FINISHED |
| Object | grandmother |
—
|
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: grandmother | Statement: [Anni-Frid Lyngstad, upbringingGuardian, grandmother]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upbringingGuardian Context triple: [Anni-Frid Lyngstad, upbringingGuardian, grandmother]
-
A.
upbringingOf
Indicates the relationship in which one entity is responsible for raising, nurturing, or providing formative care and guidance to another during its early development.
-
B.
upbringing
Indicates the relationship in which one entity raises, nurtures, and shapes the early development and values of another.
-
C.
upbringingControlledBy
Indicates that one entity has authority over and directs the upbringing or child-rearing process of another entity.
-
D.
broughtUpWith
Indicates that two individuals were raised together in the same household or close familial environment during childhood.
-
E.
parentalCare
chosen
Indicates that one entity provides nurturing, protection, or support to another in a parent-like role.
- 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_69f3499869bc8190b6c33a81686af226 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7051ad6e4819095e82bbd64761803 |
completed | May 3, 2026, 8:19 a.m. |
| PD | Predicate disambiguation | batch_69f700fe24e08190998e2c96fbaaad38 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:48 a.m.