Triple
T8841919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | When We Were Young |
E210406
|
entity |
| Predicate | mainCharacterAgePerspective |
P1924
|
FINISHED |
| Object | adult reflecting on youth |
—
|
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: adult reflecting on youth | Statement: [When We Were Young, mainCharacterAgePerspective, adult reflecting on youth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainCharacterAgePerspective Context triple: [When We Were Young, mainCharacterAgePerspective, adult reflecting on youth]
-
A.
protagonistAge
Indicates the age of the main character or central figure in a narrative or scenario.
-
B.
ageDuringNarration
Indicates that an entity has a specified age at the time when the described narrative or event is taking place.
-
C.
narrativePerspective
chosen
Indicates the point of view or vantage from which a narrative is told, specifying the relationship between the storyteller and the events being described.
-
D.
representedAgeLevel
Indicates that one entity corresponds to, or is categorized under, a particular age level or age group.
-
E.
portraysYoungerVersionOfCharacterFrom
Indicates that one character is depicted as a younger version of another character from a specified source.
- 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_69ca838967bc8190b46c3c80a2887ea4 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60876c6c8190b1b490e447e1cf4b |
completed | April 1, 2026, 12:02 a.m. |
| PD | Predicate disambiguation | batch_69cc5c25b874819084c9ba391703e066 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:48 p.m.