Triple
T18735301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret Bridge |
E458146
|
entity |
| Predicate | givesAccessVia |
P74649
|
FINISHED |
| Object | junction to Margaret Island |
—
|
LITERAL 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: junction to Margaret Island | Statement: [Margaret Bridge, givesAccessVia, junction to Margaret Island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: givesAccessVia Context triple: [Margaret Bridge, givesAccessVia, junction to Margaret Island]
-
A.
accessProvides
Indicates that one entity grants or enables the ability to use, enter, or retrieve another entity or resource.
-
B.
offersAccessVia
chosen
Indicates that one entity provides a means or channel through which another entity can be accessed or utilized.
-
C.
assumesAccessTo
Indicates that one entity presupposes or takes for granted that it has access to another entity, resource, or piece of information.
-
D.
accessIs
Indicates that one entity has the ability, permission, or means to reach, use, or interact with another entity or resource.
-
E.
typeOfAccess
Indicates the specific kind or level of access that one entity has to another (such as read, write, or execute permissions).
- F. None of above.
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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56d7ae10081908bc6857d1d147eef |
completed | April 20, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69e48d03766c8190a43f7681842f4f8d |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:51 a.m.