Triple
T25723406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Terminal |
E645050
|
entity |
| Predicate | oppositeTerminal |
P147349
|
FINISHED |
| Object | South Terminal |
—
|
NE NERFINISHED |
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: South Terminal | Statement: [North Terminal, oppositeTerminal, South Terminal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oppositeTerminal Context triple: [North Terminal, oppositeTerminal, South Terminal]
-
A.
hasOppositeTerminus
chosen
Indicates that one terminus (end point) of an entity is directly opposite or facing the terminus of another entity.
-
B.
terminusAdjacentTo
Indicates that one terminus (end point) of a route, line, or feature is directly next to or immediately bordering another terminus.
-
C.
connectsTerminus
Indicates that one entity serves as a terminus that is directly linked or joined to another entity.
-
D.
oppositeControlledBy
Indicates that one entity is under the control or influence of another entity that is positioned or defined as its opposite or counterpart.
-
E.
hasOppositeDirectionTo
Indicates that one entity’s direction is exactly reversed or opposed to the direction of another 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_69e77e8476fc8190bd5e9d05b89fad0a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
Created at: April 21, 2026, 10:07 p.m.