Triple
T4545433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snowman |
E110034
|
entity |
| Predicate | occupationBeforeCollapse |
P28984
|
FINISHED |
| Object | advertising worker |
—
|
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: advertising worker | Statement: [Snowman, occupationBeforeCollapse, advertising worker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occupationBeforeCollapse Context triple: [Snowman, occupationBeforeCollapse, advertising worker]
-
A.
earlierOccupation
chosen
Indicates that one occupation held by an entity occurred before another occupation in that entity’s work history.
-
B.
formerEconomicActivity
Indicates that an entity previously engaged in a specified economic activity but no longer does so.
-
C.
earlyOccupation
Indicates that an entity held a particular occupation or job during an early stage of its life or career.
-
D.
traditionalOccupations
Indicates that an entity is associated with occupations or jobs that are customary, long-established, or culturally traditional within a particular community or context.
-
E.
representedOccupation
Indicates that one entity has served as an official or formal representative of another entity’s occupation or professional 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_69bd4412524c8190be5bcc9ddee91848 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd57d62a8481909d5d803a582c76a1 |
completed | March 20, 2026, 2:21 p.m. |
| PD | Predicate disambiguation | batch_69bd5220e40481908ca2d7e2c43d8531 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:05 p.m.