Triple
T112889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mountain Jews |
E2284
|
entity |
| Predicate | historicalLanguage |
P7165
|
FINISHED |
| Object | Tat |
—
|
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: Tat | Statement: [Mountain Jews, historicalLanguage, Tat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalLanguage Context triple: [Mountain Jews, historicalLanguage, Tat]
-
A.
historicallySpokenIn
Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
-
B.
languageOfEarliestForm
Indicates the language in which the earliest known form or attested version of something (e.g., a text, name, or expression) is recorded.
-
C.
historicalForm
Indicates that one entity is an earlier or historically attested form or variant of another entity.
-
D.
historicalOrigin
Indicates the relationship by which one entity serves as the source, origin, or starting point in history for another entity.
-
E.
etymologicalLanguage
Indicates the language from which a word or term is historically derived in its etymology.
- F. None of above. chosen
Provenance (4 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a258808ff08190a06b6206f635612b |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a256425a488190959d71e39e699d90 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a2587e598c81909e1082b813971f48 |
completed | Feb. 28, 2026, 2:52 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.