Triple
T491347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medford, Massachusetts |
E9996
|
entity |
| Predicate | directionFromBoston |
P14099
|
FINISHED |
| Object | northwest |
—
|
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: northwest | Statement: [Medford, Massachusetts, directionFromBoston, northwest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directionFromBoston Context triple: [Medford, Massachusetts, directionFromBoston, northwest]
-
A.
distanceFromBoston
Indicates the spatial distance between a given entity’s location and the city of Boston.
-
B.
isDowntownEndpointOf
Indicates that a location serves as the downtown terminus or endpoint of a route, line, or path.
-
C.
directionFromManchesterCityCentre
Indicates the compass direction in which one location lies when measured outward from Manchester city centre.
-
D.
followingStationOnRedLineTowardAshmont
Indicates that one station is the next stop after another when traveling on the Red Line in the direction toward Ashmont.
-
E.
precedingStationOnRedLineTowardAlewife
Indicates that one station is immediately before another station on the Red Line in the direction of travel toward Alewife.
- F. None of above. chosen
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_69a2e802e2908190ab17c9479e0b6412 |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2f0f959b481908f9f28fb96695924 |
completed | Feb. 28, 2026, 1:43 p.m. |
| PD | Predicate disambiguation | batch_69a2edf7ce008190836fb6ab5ea39375 |
completed | Feb. 28, 2026, 1:30 p.m. |
| PDg | Predicate description generation | batch_69a2eebb2c908190960a4d0c014304cd |
completed | Feb. 28, 2026, 1:33 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.