Triple
T6680674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Canyon |
E151969
|
entity |
| Predicate | locatedNorthOf |
P305
|
FINISHED |
| Object | Vallejo |
E28332
|
NE 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: Vallejo | Statement: [American Canyon, locatedNorthOf, Vallejo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vallejo Context triple: [American Canyon, locatedNorthOf, Vallejo]
-
A.
Vallejo
chosen
Vallejo is a waterfront city in the San Francisco Bay Area known for its former Mare Island Naval Shipyard and diverse, working-class community.
-
B.
Vallejo
Vallejo is a metro station in Mexico City that serves passengers on Line 6 of the city’s rapid transit system.
-
C.
San Jose Diridon
San Jose Diridon is a major intermodal transit hub in San Jose, California, serving Amtrak, commuter rail, light rail, and bus services.
-
D.
Santa Cruz
Santa Cruz is a notable wine-producing city in central Chile’s Colchagua Valley, recognized for its vineyards, tourism, and colonial charm.
-
E.
Santa Cruz
Saint Croix is the largest of the U.S. Virgin Islands in the Caribbean, known for its colonial history, beaches, and coral reefs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c687f830bc81909eb8b04dbb8450b1 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6b11df8d88190bf19fcb4e7a0bdb3 |
completed | March 27, 2026, 4:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7616ff6fc8190b4e9e7810be9064b |
completed | March 28, 2026, 5:04 a.m. |
Created at: March 27, 2026, 2:04 p.m.