Triple
T36349999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | N40 |
E895174
|
entity |
| Predicate | includesTollStructure |
P3376
|
FINISHED |
| Object | Jack Lynch Tunnel (historically tolled) |
E381318
|
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: Jack Lynch Tunnel (historically tolled) | Statement: [N40, includesTollStructure, Jack Lynch Tunnel (historically tolled)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesTollStructure Context triple: [N40, includesTollStructure, Jack Lynch Tunnel (historically tolled)]
-
A.
hasTollVariant
Indicates that an entity has a version or instance that requires paying a toll or fee for use or access.
-
B.
hasTollSegment
chosen
Indicates that a route, road, or path includes a segment where a toll must be paid.
-
C.
hasToll
Indicates that the use, access, or passage associated with something requires payment of a toll or fee.
-
D.
appliesTollTo
Indicates that a fee or charge is imposed on a subject for using, accessing, or passing through something.
-
E.
hasTollForTrucks
Indicates that a toll or fee is required specifically for trucks when using a particular road, route, or facility.
- F. None of above.
Provenance (4 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_69f76e4f437c8190a1af3ea2564f41f5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39c3fa3270819091d20307884644d0 |
completed | June 22, 2026, 11:23 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:09 p.m.