Triple
T8998685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Garret Hostel Lane |
E214986
|
entity |
| Predicate | connectsAreasOf |
P24718
|
FINISHED |
| Object | central Cambridge |
—
|
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: central Cambridge | Statement: [Garret Hostel Lane, connectsAreasOf, central Cambridge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsAreasOf Context triple: [Garret Hostel Lane, connectsAreasOf, central Cambridge]
-
A.
connectsArea
Indicates that one area serves as a link or passage between two other areas, enabling movement or interaction between them.
-
B.
connectsRegions
chosen
Indicates a relationship where one entity links or joins two or more distinct regions, enabling passage, interaction, or continuity between them.
-
C.
connectsCommercialAreas
Indicates a relationship where one entity links or provides direct access between two or more commercial areas or business districts.
-
D.
connectsIslands
Indicates a relationship where something (such as a structure, route, or link) joins or provides passage between two or more islands.
-
E.
connectsPartOf
Indicates a relationship where one entity serves to link or join a component to the larger whole of which that component is a part.
- 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_69ca83a12d648190b1e4fe11e8a31890 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc68e23734819083a98f4ff0942479 |
completed | April 1, 2026, 12:37 a.m. |
| PD | Predicate disambiguation | batch_69cc5edd6cb48190b4fc6d6ca0418056 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:05 p.m.