Triple
T2017532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Strawberry Creek |
E44029
|
entity |
| Predicate | passesLandmark |
P8340
|
FINISHED |
| Object |
Faculty Glade
Faculty Glade is a scenic, tree-lined meadow on the UC Berkeley campus known as a quiet gathering and relaxation spot for students and faculty.
|
E224565
|
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: Faculty Glade | Statement: [Strawberry Creek, passesLandmark, Faculty Glade]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Faculty Glade Context triple: [Strawberry Creek, passesLandmark, Faculty Glade]
-
A.
Deans
Deans is an unincorporated community located within South Brunswick Township in Middlesex County, New Jersey.
-
B.
Deans
Deans is a residential and industrial area within the town of Livingston in West Lothian, Scotland.
-
C.
Professor Burris
Professor Burris is the skeptical psychology professor and narrator of B.F. Skinner’s utopian novel "Walden Two," through whose perspective the experimental community is explored and critiqued.
-
D.
Dean
Dean is a masculine given name of English origin commonly used in many English-speaking countries.
-
E.
Professor Brand
Professor Brand is a brilliant but morally conflicted NASA physicist in the film "Interstellar," whose secretive plan to save humanity drives much of the story’s tension.
- 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: Faculty Glade Triple: [Strawberry Creek, passesLandmark, Faculty Glade]
Generated description
Faculty Glade is a scenic, tree-lined meadow on the UC Berkeley campus known as a quiet gathering and relaxation spot for students and faculty.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Faculty Glade Target entity description: Faculty Glade is a scenic, tree-lined meadow on the UC Berkeley campus known as a quiet gathering and relaxation spot for students and faculty.
-
A.
Deans
Deans is an unincorporated community located within South Brunswick Township in Middlesex County, New Jersey.
-
B.
Deans
Deans is a residential and industrial area within the town of Livingston in West Lothian, Scotland.
-
C.
Professor Burris
Professor Burris is the skeptical psychology professor and narrator of B.F. Skinner’s utopian novel "Walden Two," through whose perspective the experimental community is explored and critiqued.
-
D.
Dean
Dean is a masculine given name of English origin commonly used in many English-speaking countries.
-
E.
Professor Brand
Professor Brand is a brilliant but morally conflicted NASA physicist in the film "Interstellar," whose secretive plan to save humanity drives much of the story’s tension.
- 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_69a8891201bc8190aca837be6de41579 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb8ce71788190ac21beff10b08122 |
completed | March 7, 2026, 5:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae0af1547481909d5f2ca9c4715ace |
completed | March 8, 2026, 11:49 p.m. |
| NEDg | Description generation | batch_69ae0b78340c8190897a8cbba418cb00 |
completed | March 8, 2026, 11:51 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae0c01b30c81908394e31aa3238bfa |
completed | March 8, 2026, 11:53 p.m. |
Created at: March 4, 2026, 7:38 p.m.