Triple
T18977132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 51st station (Green Line) |
E464323
|
entity |
| Predicate | hasDirectionServed |
P48943
|
FINISHED |
| Object | northbound |
—
|
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: northbound | Statement: [51st station (Green Line), hasDirectionServed, northbound]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectionServed Context triple: [51st station (Green Line), hasDirectionServed, northbound]
-
A.
servesDirection
Indicates that one entity provides service or functionality oriented toward, or in the direction of, another entity.
-
B.
servedByDirection
chosen
Indicates that something (such as a route, service, or facility) is provided or accessed in a specific directional orientation (e.g., northbound, inbound).
-
C.
isServedAt
Indicates that something (such as food, drink, or a service) is provided or made available at a particular place or venue.
-
D.
isServed
Indicates that one entity provides or delivers a service, product, or assistance to another entity.
-
E.
servedDestination
Indicates that a service or action is directed toward, or provided to, a particular destination.
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d620bba48190a300dba9733592b0 |
completed | April 20, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f437648190b85650dae8885d48 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, noon