Triple
T37235788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Sunless City |
E923568
|
entity |
| Predicate | inUniverseTransportation |
P85330
|
FINISHED |
| Object | submarine |
—
|
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: submarine | Statement: [The Sunless City, inUniverseTransportation, submarine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inUniverseTransportation Context triple: [The Sunless City, inUniverseTransportation, submarine]
-
A.
transportation
Indicates the movement of someone or something from one place to another, typically using a vehicle or transit system.
-
B.
transports
Indicates that one entity carries or conveys another entity from one place to another.
-
C.
transportationContext
Indicates the situational or environmental conditions under which transportation occurs, such as mode, purpose, or circumstances of travel.
-
D.
showsTransportation
Indicates that one entity presents or depicts a means or mode of transportation associated with another entity.
-
E.
isTransportationType
chosen
Indicates that one entity functions as a mode or category of transportation for the other entity.
- 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_69f76ea9fee88190a589f661d95a7189 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd5f29b1988190877764ef2a399c7f |
completed | May 8, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_69fd5e30194c819085b5ce586122ab37 |
completed | May 8, 2026, 3:53 a.m. |
Created at: May 3, 2026, 4:15 p.m.