Triple
T35958121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Selonians |
E1039922
|
entity |
| Predicate | assimilationWith |
P70215
|
FINISHED |
| Object | Latgalians |
—
|
NE NERFINISHED |
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: Latgalians | Statement: [Selonians, assimilationWith, Latgalians]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: assimilationWith Context triple: [Selonians, assimilationWith, Latgalians]
-
A.
languageOfAssimilation
Indicates the language used to integrate or absorb individuals or groups into a dominant culture or society.
-
B.
culturalAssimilationInto
chosen
Indicates a process where one entity adopts or integrates into the cultural norms, values, and practices of another entity or group.
-
C.
linguisticAssimilation
Indicates the process by which one language or linguistic feature becomes more similar to or integrated with another through contact or influence.
-
D.
naturalizes
Indicates the process by which an entity (often a person or practice) is made to appear normal, inherent, or taken-for-granted within a particular system or context.
-
E.
absorbed
Indicates that one entity takes in, soaks up, or assimilates another entity or substance.
- 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_69f76e26b21081909fd9ffb3aff6c77a |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7ac23d1388190bdf9628b294943bd |
completed | May 3, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69f7ab734d848190a84f9b8c3a952b75 |
completed | May 3, 2026, 8:09 p.m. |
Created at: May 3, 2026, 4:07 p.m.