Triple
T22866359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boii |
E567064
|
entity |
| Predicate | alliedWith |
P37
|
FINISHED |
| Object | Insubres |
—
|
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: Insubres | Statement: [Boii, alliedWith, Insubres]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Insubres Context triple: [Boii, alliedWith, Insubres]
-
A.
Insubres
chosen
The Insubres were an ancient Celtic people of northern Italy, centered around Mediolanum (modern Milan), known for their resistance to Roman expansion before eventual incorporation into the Roman Republic.
-
B.
Insubric
Insubric is a group of closely related Gallo-Italic dialects spoken in parts of northern Italy and southern Switzerland, including the area around Luino.
-
C.
Inunhan
Inunhan is a regional dialect of the Romblomanon language spoken by communities in the province of Romblon in the Philippines.
-
D.
Isanzu
Isanzu is a Bantu language spoken by the Isanzu people of north-central Tanzania.
-
E.
Rascia
Rascia is a historical region in the central Balkans that formed the medieval core of the Serbian state.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e24589083081908d5694c4fdc80086 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f00f21081909b771610549c5757 |
completed | April 29, 2026, 3:46 a.m. |
Created at: April 17, 2026, 3:38 p.m.