Triple
T1741302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Embarcadero |
E38238
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Pier 3
Pier 3 is a historic waterfront pier along San Francisco’s Embarcadero, known for its maritime heritage and scenic views of the bay.
|
E203039
|
NE FINISHED |
How this triple was built (4 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 3 | Statement: [Embarcadero, hasPart, Pier 3]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pier 3 Context triple: [Embarcadero, hasPart, Pier 3]
-
A.
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.
-
B.
Pier 33
Pier 33 is a waterfront terminal in San Francisco that serves as the primary departure point for ferry trips to Alcatraz Island.
-
C.
Pier 57
Pier 57 is a historic waterfront pier and entertainment complex on Seattle’s Elliott Bay, featuring restaurants, shops, and attractions along the city’s central waterfront.
-
D.
Pier A
Pier A is a major passenger terminal concourse at Brussels Airport primarily serving Schengen and some non-Schengen flights.
-
E.
Pier 68
Pier 68 is a public recreational pier and park on Philadelphia’s Delaware River waterfront, known for its fishing spots, river views, and landscaped green space.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Pier 3 Triple: [Embarcadero, hasPart, Pier 3]
Generated description
Pier 3 is a historic waterfront pier along San Francisco’s Embarcadero, known for its maritime heritage and scenic views of the bay.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Pier 3 Target entity description: Pier 3 is a historic waterfront pier along San Francisco’s Embarcadero, known for its maritime heritage and scenic views of the bay.
-
A.
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.
-
B.
Pier 33
Pier 33 is a waterfront terminal in San Francisco that serves as the primary departure point for ferry trips to Alcatraz Island.
-
C.
Pier 57
Pier 57 is a historic waterfront pier and entertainment complex on Seattle’s Elliott Bay, featuring restaurants, shops, and attractions along the city’s central waterfront.
-
D.
Pier A
Pier A is a major passenger terminal concourse at Brussels Airport primarily serving Schengen and some non-Schengen flights.
-
E.
Pier 68
Pier 68 is a public recreational pier and park on Philadelphia’s Delaware River waterfront, known for its fishing spots, river views, and landscaped green space.
- F. None of above. chosen
Provenance (5 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_69a8862b01a48190ab47209063af82d9 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa63c5ab648190bceae2a19fa18e87 |
completed | March 6, 2026, 5:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adbf498848819085cd7faffd86cd77 |
completed | March 8, 2026, 6:26 p.m. |
| NEDg | Description generation | batch_69adbff135188190908058a2e2d41a1e |
completed | March 8, 2026, 6:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69adc0832cd881909702f380412702d5 |
completed | March 8, 2026, 6:31 p.m. |
Created at: March 4, 2026, 7:30 p.m.