Triple
T2936208
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phoebe Caulfield |
E79273
|
entity |
| Predicate | ageInWork |
P17574
|
FINISHED |
| Object | about ten years old |
—
|
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: about ten years old | Statement: [Phoebe Caulfield, ageInWork, about ten years old]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageInWork Context triple: [Phoebe Caulfield, ageInWork, about ten years old]
-
A.
ageInPrimaryWork
chosen
Indicates the age of an entity (typically a person or character) within the context of their primary work or main creative output.
-
B.
ageAtStartOfRole
Indicates the age an entity was when they first began a specified role or position.
-
C.
hasWorkedFor
Indicates that an entity has been employed by or has provided work or services to another entity.
-
D.
retirementYear
Indicates the specific year in which an entity retires or is officially considered retired.
-
E.
hasAge
Indicates that an entity possesses a specific age value, typically expressed as a number of time units since its birth or creation.
- 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_69ad8b0fbab081908f6a61567c045d8d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad983df5e08190939cd8acf8ad5b55 |
completed | March 8, 2026, 3:39 p.m. |
| PD | Predicate disambiguation | batch_69ad96088fb481909976b436c2b729d9 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:56 p.m.