Triple
T612726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gdynia |
E12134
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Sea Towers
Sea Towers is a prominent modern high-rise residential and office complex on the waterfront of Gdynia, Poland.
|
E76542
|
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: Sea Towers | Statement: [Gdynia, hasLandmark, Sea Towers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sea Towers Context triple: [Gdynia, hasLandmark, Sea Towers]
-
A.
Pollack Hall
Pollack Hall is a prominent concert and performance venue associated with McGill University's Schulich School of Music in Montreal, Canada.
-
B.
Durfee Hall
Durfee Hall is a historic residential dormitory located on Yale University's Old Campus in New Haven, Connecticut.
-
C.
Hollis Hall
Hollis Hall is one of Harvard University's historic brick dormitories, located in Harvard Yard and traditionally housing first-year students.
-
D.
Sibley Hall
Sibley Hall is a historic academic building on Cornell University’s Arts Quad, known for housing the College of Architecture, Art, and Planning.
-
E.
Aldrich Hall
Aldrich Hall is a primary classroom and academic building at Harvard Business School, known for hosting many of the school’s MBA courses and case-method discussions.
- 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: Sea Towers Triple: [Gdynia, hasLandmark, Sea Towers]
Generated description
Sea Towers is a prominent modern high-rise residential and office complex on the waterfront of Gdynia, Poland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sea Towers Target entity description: Sea Towers is a prominent modern high-rise residential and office complex on the waterfront of Gdynia, Poland.
-
A.
Pollack Hall
Pollack Hall is a prominent concert and performance venue associated with McGill University's Schulich School of Music in Montreal, Canada.
-
B.
Durfee Hall
Durfee Hall is a historic residential dormitory located on Yale University's Old Campus in New Haven, Connecticut.
-
C.
Hollis Hall
Hollis Hall is one of Harvard University's historic brick dormitories, located in Harvard Yard and traditionally housing first-year students.
-
D.
Sibley Hall
Sibley Hall is a historic academic building on Cornell University’s Arts Quad, known for housing the College of Architecture, Art, and Planning.
-
E.
Aldrich Hall
Aldrich Hall is a primary classroom and academic building at Harvard Business School, known for hosting many of the school’s MBA courses and case-method discussions.
- 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_69a493309df48190a327f748e88049a6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49e08dbf88190ab050078a63e266b |
completed | March 1, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a533dabe288190ab25bd6d76e79d06 |
completed | March 2, 2026, 6:53 a.m. |
| NEDg | Description generation | batch_69a54e4849f48190868d7b624e450dc3 |
completed | March 2, 2026, 8:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a55048e2ec81908d306f44b2ca24fa |
completed | March 2, 2026, 8:54 a.m. |
Created at: March 1, 2026, 7:35 p.m.