Triple
T35766310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tectosages |
E1034023
|
entity |
| Predicate | regionRomanizedAs |
P165754
|
FINISHED |
| Object | Roman province of Galatia |
—
|
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: Roman province of Galatia | Statement: [Tectosages, regionRomanizedAs, Roman province of Galatia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionRomanizedAs Context triple: [Tectosages, regionRomanizedAs, Roman province of Galatia]
-
A.
romanizationRegion
chosen
Indicates the region or locale whose conventions are used to romanize a name, term, or text.
-
B.
nameInLanguageRomanization
Indicates that an entity’s name is represented in the romanized (Latin-script) form of a particular language.
-
C.
exampleRomanization
Indicates that one entity is a romanized representation (in Latin script) of the other entity’s original text or name.
-
D.
hasRomanizationOf
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
E.
countryOfEntityRomanized
Indicates the country associated with an entity, expressed using a romanized (Latin-script) form of the country name.
- 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_69f76e13edd081909101629aa829c4ad |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ffecdcbac4819093b725a7dbe0e61b |
completed | May 10, 2026, 2:26 a.m. |
| PD | Predicate disambiguation | batch_69ffec3633288190adbbd84e277708dc |
completed | May 10, 2026, 2:23 a.m. |
Created at: May 3, 2026, 4:06 p.m.