Triple
T16586994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Embarcadero, San Francisco |
E402984
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Pier 27 |
E396476
|
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: Pier 27 | Statement: [Embarcadero, San Francisco, hasLandmark, Pier 27]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pier 27 Context triple: [Embarcadero, San Francisco, hasLandmark, Pier 27]
-
A.
Pier 27
chosen
Pier 27 is a waterfront facility in San Francisco that serves as a major cruise ship terminal and gateway for passengers visiting the city.
-
B.
Pier 7
Pier 7 is one of the waterfront recreational piers within Brooklyn Bridge Park in Brooklyn, New York, offering public access and views along the East River.
-
C.
Pier 7
Pier 7 is a scenic wooden pier on San Francisco’s Embarcadero waterfront, known for its skyline views, fishing spots, and iconic perspective toward the Financial District.
-
D.
Pier 7
Pier 7 is a multi-story dining and entertainment tower in Dubai Marina known for its collection of upscale restaurants and panoramic waterfront views.
-
E.
Pier 23
Pier 23 is a historic waterfront spot along San Francisco’s Embarcadero known for its casual seafood restaurant, bar, and scenic bay views.
- 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_69d88387363c8190a97a0c942130de97 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3599daa508190a9ed6f64138c0e53 |
completed | April 18, 2026, 10:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00b278f85081909b3dd5ae5dbc4f8a |
completed | May 10, 2026, 4:29 p.m. |
Created at: April 10, 2026, 5:16 a.m.