Triple
T33124696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eveline |
E847689
|
entity |
| Predicate | takesPlaceBeforeEvent |
P160657
|
FINISHED |
| Object | emigration to Argentina |
—
|
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: emigration to Argentina | Statement: [Eveline, takesPlaceBeforeEvent, emigration to Argentina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: takesPlaceBeforeEvent Context triple: [Eveline, takesPlaceBeforeEvent, emigration to Argentina]
-
A.
actsBefore
chosen
Indicates that one entity performs an action or occurs in time prior to another entity or action.
-
B.
heldBefore
Indicates that one entity possessed or maintained control of something at an earlier time than another entity or event.
-
C.
heirBeforeEvent
Indicates that one entity is designated as the heir of another prior to a specified event occurring.
-
D.
diesBeforeEvent
Indicates that the subject entity dies at a point in time that occurs before the specified event takes place.
-
E.
appearsBefore
Indicates that one entity occurs, is positioned, or is presented earlier in an ordered sequence than another entity.
- 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_69f349588f088190b7c9588860f72033 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d71dc75c8190886ea8c2ab87b323 |
completed | May 3, 2026, 5:03 a.m. |
| PD | Predicate disambiguation | batch_69f6d27224708190b31a541cebe0ff77 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:27 a.m.