Triple
T4448778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alton Line |
E96355
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Alton |
E102479
|
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: Alton | Statement: [Alton Line, connects, Alton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alton Context triple: [Alton Line, connects, Alton]
-
A.
Alton, Illinois
Alton, Illinois is a historic Mississippi River city in southwestern Illinois known for its limestone bluffs, Civil War and abolitionist history, and role as a regional industrial and transportation hub.
-
B.
ALTON
chosen
ALTON is a historic market town in Hampshire, England, known for its rural surroundings and connections to the author Jane Austen.
-
C.
Collinsville
Collinsville is a small unincorporated community and census-designated place located in the Sacramento–San Joaquin River Delta region of Northern California.
-
D.
Collinsville
Collinsville is a historic village area within the town of Dracut, Massachusetts, known for its preserved New England character and local heritage.
-
E.
Supaul
Supaul is a town in the Indian state of Bihar known primarily as an administrative and commercial center for the surrounding region.
- 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_69b345415ba481908df738e7174448ba |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355d45b748190b09b7067fc6279b0 |
completed | March 13, 2026, 12:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bb61047c88819080943c2ce62c0ffd |
completed | March 19, 2026, 2:35 a.m. |
Created at: March 12, 2026, 11:32 p.m.