Triple
T8327840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bomi County |
E194998
|
entity |
| Predicate | administrativeCenter |
P1474
|
FINISHED |
| Object | Tubmanburg |
E725273
|
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: Tubmanburg | Statement: [Bomi County, administrativeCenter, Tubmanburg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tubmanburg Context triple: [Bomi County, administrativeCenter, Tubmanburg]
-
A.
Tubmanburg
chosen
Tubmanburg is a town in western Liberia that serves as the administrative and commercial center of Bomi County.
-
B.
Boitsfort
Boitsfort is a locality in the Brussels-Capital Region of Belgium, known for its residential character and proximity to the Sonian Forest.
-
C.
Crotonville
Crotonville is a small hamlet within the town of Ossining in Westchester County, New York.
-
D.
Reister’s Town
Reister’s Town was the original name of what is now Reisterstown, a historic community in Maryland that developed as a key stop along early travel routes northwest of Baltimore.
-
E.
Montarville
Montarville is a Canadian federal electoral district located in Quebec, represented in the House of Commons.
- 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_69ca82e87f2c8190bdb71ee29dfc642d |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7f8243288190b1ae74d69395fc91 |
completed | March 31, 2026, 8:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc70723a48190a3e33908fc84fe59 |
completed | April 2, 2026, 1:31 a.m. |
Created at: March 30, 2026, 5:56 p.m.