Triple
T21287980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fremont |
E524711
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Fremont Troll |
—
|
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: Fremont Troll | Statement: [Fremont, hasLandmark, Fremont Troll]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fremont Troll Context triple: [Fremont, hasLandmark, Fremont Troll]
-
A.
Fremont Troll
chosen
The Fremont Troll is a large, whimsical concrete sculpture of a troll clutching a real Volkswagen Beetle beneath the Aurora Bridge in Seattle’s Fremont neighborhood.
-
B.
Ferris
Ferris is a small suburban city in the Dallas–Fort Worth metropolitan area in Texas.
-
C.
Ferris
Ferris is a surname most notably associated with British actress Pam Ferris, known for her roles in film, television, and theatre.
-
D.
Rainier Tower
Rainier Tower is a distinctive high-rise office building in downtown Seattle, Washington, best known for its unusual design featuring a narrow, flared concrete base supporting a wider upper structure.
-
E.
Bromo Seltzer Tower
The Bromo Seltzer Tower is a historic early-20th-century clock tower and former advertising landmark in downtown Baltimore, Maryland.
- 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_69e0b5171f6c8190a5d57201ede73811 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e736d7c57c8190bc4180ea590a62d4 |
completed | April 21, 2026, 8:35 a.m. |
Created at: April 16, 2026, 4:03 p.m.