Triple
T28766446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mukilteo ferry terminal |
E726283
|
entity |
| Predicate | primaryLinkBetween |
P69345
|
FINISHED |
| Object | Mukilteo, Washington |
—
|
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: Mukilteo, Washington | Statement: [Mukilteo ferry terminal, primaryLinkBetween, Mukilteo, Washington]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryLinkBetween Context triple: [Mukilteo ferry terminal, primaryLinkBetween, Mukilteo, Washington]
-
A.
primaryReference
Indicates that one entity serves as the main or authoritative source of information or citation for another entity.
-
B.
primaryRailLinkFor
Indicates that one entity serves as the main or principal rail connection or route for another entity.
-
C.
formsPrimaryLinkBetween
chosen
Indicates that one entity serves as the main or most important connection or linkage between two other entities.
-
D.
primaryConnections
Indicates that there exists a main or most significant relationship or linkage between entities, distinguishing these connections from secondary or peripheral ones.
-
E.
primaryReferent
Indicates that one entity is the main or most salient referent associated with another entity among potentially multiple candidates.
- 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_69f03198be14819098fa74e48b3749bf |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_6a00781b749c8190921c46e110cae0b0 |
completed | May 10, 2026, 12:20 p.m. |
| PD | Predicate disambiguation | batch_6a0077df3c8481909fabc9e84f5936e3 |
completed | May 10, 2026, 12:19 p.m. |
Created at: April 28, 2026, 6:13 a.m.