Triple
T16567933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bura |
E402509
|
entity |
| Predicate | hasNeighborLanguage |
P16383
|
FINISHED |
| Object | Margi |
E356866
|
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: Margi | Statement: [Bura, hasNeighborLanguage, Margi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Margi Context triple: [Bura, hasNeighborLanguage, Margi]
-
A.
Margi
chosen
Margi are an ethnic group native to northeastern Nigeria, particularly in and around Adamawa State, known for their distinct language and cultural traditions.
-
B.
Margalo
Margalo is a kind and resourceful bird who becomes one of Stuart Little’s closest companions in E.B. White’s classic children’s novel.
-
C.
Margi Babal
Margi Babal is a subgroup of the Margi people, an ethnic community primarily found in northeastern Nigeria.
-
D.
Marlo
Marlo is a small coastal town in East Gippsland, Victoria, Australia, known for its location near the mouth of the Snowy River and its fishing and outdoor recreation.
-
E.
Marlo
Marlo is a fictional character associated with Tully, likely appearing in a narrative centered on that figure.
- 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_69d8838648088190acf97ef11fc3f61b |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35772f6608190a125c7d3c199c3e2 |
completed | April 18, 2026, 10:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006ee3dcbc819087ea66b262585232 |
completed | May 10, 2026, 11:41 a.m. |
Created at: April 10, 2026, 5:16 a.m.