Triple
T9200657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A12 |
E220828
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Witham |
E97765
|
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: Witham | Statement: [A12, serves, Witham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Witham Context triple: [A12, serves, Witham]
-
A.
Witham
chosen
Witham is a town in the county of Essex, England, known as a residential and commuter community between Chelmsford and Colchester.
-
B.
Lyme Brook
Lyme Brook is a small watercourse flowing through the Newcastle-under-Lyme area in Staffordshire, England.
-
C.
Scituate
Scituate is a coastal town in Plymouth County, Massachusetts, known for its historic harbor, beaches, and maritime character on the state's South Shore.
-
D.
Scituate
Scituate is a rural town in central Rhode Island known for its reservoirs, woodlands, and historic New England character.
-
E.
Mill Plain
Mill Plain is a major arterial corridor in Vancouver, Washington, serving as a key route for local traffic, transit, and commercial activity.
- 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_69ca83e8e9248190862cf3e41693b310 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd9429b448190a078e9cdfedd4918 |
completed | April 1, 2026, 8:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d065dbcf908190a6e36cef879cd31b |
completed | April 4, 2026, 1:14 a.m. |
Created at: March 30, 2026, 7:25 p.m.