Triple
T2146261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcomanni |
E47071
|
entity |
| Predicate | ruler |
P403
|
FINISHED |
| Object | Ballomar |
E45672
|
NE 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: Ballomar | Statement: [Marcomanni, ruler, Ballomar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ballomar Context triple: [Marcomanni, ruler, Ballomar]
-
A.
Ballomar
chosen
Ballomar was a 2nd-century chieftain of the Marcomanni who led major Germanic incursions into the Roman Empire during the Marcomannic Wars.
-
B.
The Ball
"The Ball" is a short story by renowned Japanese author Ryūnosuke Akutagawa, reflecting his characteristic blend of psychological insight and modernist narrative style.
-
C.
The Ball
The Ball is the popular nickname for Reunion Tower, a distinctive geodesic observation tower and Dallas landmark known for its glowing spherical top.
-
D.
Ballasalla
Ballasalla is a small village on the Isle of Man, known for its historic Rushen Abbey and proximity to the island’s former capital, Castletown.
-
E.
Bola
Bola is the given name of Bola Tinubu, a prominent Nigerian politician and current president of Nigeria.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88a1933e0819094f18426ed74180f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe25d8848190a3ba691668a68e37 |
completed | March 7, 2026, 5:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae51b94d3881909bd619e34e26e6c4 |
completed | March 9, 2026, 4:51 a.m. |
Created at: March 4, 2026, 7:44 p.m.