Triple
T18720560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angel Island |
E457761
|
entity |
| Predicate | ferryServiceFrom |
P1737
|
FINISHED |
| Object | Tiburon |
—
|
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: Tiburon | Statement: [Angel Island, ferryServiceFrom, Tiburon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tiburon Context triple: [Angel Island, ferryServiceFrom, Tiburon]
-
A.
Tiburon
chosen
Tiburon is a small, affluent waterfront town in Marin County, California, known for its scenic views of San Francisco Bay and ferry access to nearby islands.
-
B.
Tiburon
Tiburon is a coastal commune in southwestern Haiti known for its location on the Tiburon Peninsula along the Caribbean Sea.
-
C.
Barracuda
Barracuda is Seagate Technology’s long-running family of consumer and desktop hard disk drives known for high capacity and mainstream performance.
-
D.
Barracuda
Barracuda is a tropical-style rum-based cocktail typically featuring pineapple and lime flavors, often served as a refreshing, fruity mixed drink.
-
E.
Marlin
Marlin is a surname most notably associated with American stock car racing driver Sterling Marlin.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d393ba9c8190a8b03b04ddbb0a09 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56ab9e0dc8190bf579d7e89e941f4 |
completed | April 19, 2026, 11:52 p.m. |
Created at: April 10, 2026, 11:50 a.m.