Triple
T10788972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Massachusetts Route 107 |
E254525
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | Route 107 |
E14855
|
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: Route 107 | Statement: [Massachusetts Route 107, abbreviation, Route 107]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Route 107 Context triple: [Massachusetts Route 107, abbreviation, Route 107]
-
A.
Route 107
Route 107 is a state highway in southwestern Connecticut that serves as a local connector through towns such as Redding and Georgetown.
-
B.
Route 107
chosen
Route 107 is a state highway in Massachusetts that runs through cities such as Revere and Lynn, serving as a key north–south arterial route north of Boston.
-
C.
Route 110
Route 110 is a poem by Seamus Heaney that reimagines episodes from Homer’s Odyssey within the landscapes and experiences of modern Ireland.
-
D.
Route 108
Route 108 is a regional road that passes through the district of Uruca, serving as part of the local transportation network.
-
E.
Route 117
Route 117 is a state highway in Maine that runs through several counties, connecting multiple towns and serving as a regional north–south and east–west corridor.
- 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732f4b1388190a1364e56a90e8388 |
completed | April 9, 2026, 5:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de562873b081908bea08c56b1c1e3f |
completed | April 14, 2026, 2:58 p.m. |
Created at: April 8, 2026, 9:17 p.m.