Triple
T2927029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | McKeldin Mall |
E78869
|
entity |
| Predicate | surroundedBy |
P224
|
FINISHED |
| Object |
Woods Hall
Woods Hall is an academic building on the University of Maryland’s College Park campus, located along the prominent McKeldin Mall.
|
E311081
|
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: Woods Hall | Statement: [McKeldin Mall, surroundedBy, Woods Hall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Woods Hall Context triple: [McKeldin Mall, surroundedBy, Woods Hall]
-
A.
Hodge Hall
Hodge Hall is an academic building on the campus of Princeton Theological Seminary, used for theological instruction and related institutional activities.
-
B.
Bingham Hall
Bingham Hall is a historic Yale University dormitory located on the Old Campus in New Haven, Connecticut.
-
C.
Evans Hall
Evans Hall is a prominent academic building on the UC Berkeley campus that long housed the university’s mathematics and statistics departments and is known for its stark modernist architecture.
-
D.
Lewis Hall
Lewis Hall is a building located adjacent to Latimer Hall, likely part of an academic or institutional campus.
-
E.
Hudson Hall
Hudson Hall is a primary academic and research building of Duke University's Pratt School of Engineering, housing classrooms, laboratories, and faculty offices.
- 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: Woods Hall Triple: [McKeldin Mall, surroundedBy, Woods Hall]
Generated description
Woods Hall is an academic building on the University of Maryland’s College Park campus, located along the prominent McKeldin Mall.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Woods Hall Target entity description: Woods Hall is an academic building on the University of Maryland’s College Park campus, located along the prominent McKeldin Mall.
-
A.
Hodge Hall
Hodge Hall is an academic building on the campus of Princeton Theological Seminary, used for theological instruction and related institutional activities.
-
B.
Bingham Hall
Bingham Hall is a historic Yale University dormitory located on the Old Campus in New Haven, Connecticut.
-
C.
Evans Hall
Evans Hall is a prominent academic building on the UC Berkeley campus that long housed the university’s mathematics and statistics departments and is known for its stark modernist architecture.
-
D.
Lewis Hall
Lewis Hall is a building located adjacent to Latimer Hall, likely part of an academic or institutional campus.
-
E.
Hudson Hall
Hudson Hall is a primary academic and research building of Duke University's Pratt School of Engineering, housing classrooms, laboratories, and faculty offices.
- 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_69ad8b0d40b481908bc2a5fa2e73c3fb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad97fd89d88190bc7db4b39058ae3a |
completed | March 8, 2026, 3:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b08668a204819082b13e6ce62d5728 |
completed | March 10, 2026, 9 p.m. |
| NEDg | Description generation | batch_69b0d18f7928819098fba6a23dd40230 |
completed | March 11, 2026, 2:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b0d221ec2481909c9d42f1c0d86b9b |
completed | March 11, 2026, 2:23 a.m. |
Created at: March 8, 2026, 2:55 p.m.