Triple
T4082960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gramercy |
E87520
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Irving Place
Irving Place is a historic street in Manhattan, New York City, known for its 19th-century architecture and cultural landmarks near the Gramercy Park area.
|
E498960
|
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: Irving Place | Statement: [Gramercy, hasLandmark, Irving Place]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Irving Place Context triple: [Gramercy, hasLandmark, Irving Place]
-
A.
Nevins Street
Nevins Street is a New York City Subway station in Downtown Brooklyn that serves as a key stop on the IRT Eastern Parkway Line.
-
B.
Harrison Street
Harrison Street is a major thoroughfare in Oakland, California, running through areas including the historic Chinatown neighborhood.
-
C.
Keefer Street
Keefer Street is a notable thoroughfare in Vancouver’s Chinatown, known for its historic buildings, cultural landmarks, and vibrant local businesses.
-
D.
Judd Street
Judd Street is a central London street in the Borough of Camden that hosts the main administrative offices of the local authority.
-
E.
Flora Street
Flora Street is a prominent thoroughfare in Dallas’s Arts District, known for housing major cultural venues and performance spaces.
- 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: Irving Place Triple: [Gramercy, hasLandmark, Irving Place]
Generated description
Irving Place is a historic street in Manhattan, New York City, known for its 19th-century architecture and cultural landmarks near the Gramercy Park area.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Irving Place Target entity description: Irving Place is a historic street in Manhattan, New York City, known for its 19th-century architecture and cultural landmarks near the Gramercy Park area.
-
A.
Nevins Street
Nevins Street is a New York City Subway station in Downtown Brooklyn that serves as a key stop on the IRT Eastern Parkway Line.
-
B.
Harrison Street
Harrison Street is a major thoroughfare in Oakland, California, running through areas including the historic Chinatown neighborhood.
-
C.
Keefer Street
Keefer Street is a notable thoroughfare in Vancouver’s Chinatown, known for its historic buildings, cultural landmarks, and vibrant local businesses.
-
D.
Judd Street
Judd Street is a central London street in the Borough of Camden that hosts the main administrative offices of the local authority.
-
E.
Flora Street
Flora Street is a prominent thoroughfare in Dallas’s Arts District, known for housing major cultural venues and performance spaces.
- 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_69aed9435cf48190ad1da737c962d19d |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefc7933b481909bb3e02c6c04c8ee |
completed | March 9, 2026, 4:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bed8f8a8a08190b403b8c3caf20009 |
completed | March 21, 2026, 5:44 p.m. |
| NEDg | Description generation | batch_69bed9c4bd98819089c9d656379a959d |
completed | March 21, 2026, 5:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69beda1519348190a09e01ce4464bccc |
completed | March 21, 2026, 5:49 p.m. |
Created at: March 9, 2026, 3:39 p.m.