Triple
T845168
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Columbia University |
E18260
|
entity |
| Predicate | colors |
P60
|
FINISHED |
| Object |
Columbia blue
Columbia blue is a light, powdery shade of blue traditionally associated with and popularized by Columbia University.
|
E99597
|
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: Columbia blue | Statement: [Columbia University, colors, Columbia blue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Columbia blue Context triple: [Columbia University, colors, Columbia blue]
-
A.
Duke blue
Duke blue is the distinctive deep royal blue shade associated with Duke University’s branding and athletic teams.
-
B.
Yale Blue
Yale Blue is a deep, rich shade of blue traditionally associated with academic institutions and collegiate branding.
-
C.
Berkeley Blue
Berkeley Blue is a deep navy shade that serves as one of the primary official colors representing the University of California, Berkeley.
-
D.
Oxford blue
Oxford blue is a dark, rich shade of navy traditionally associated with the University of Oxford and its sports teams.
-
E.
the Blue
The Blue is the traditional nickname and spirit symbol representing Phillips Academy Andover’s athletic teams and school community.
- 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: Columbia blue Triple: [Columbia University, colors, Columbia blue]
Generated description
Columbia blue is a light, powdery shade of blue traditionally associated with and popularized by Columbia University.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Columbia blue Target entity description: Columbia blue is a light, powdery shade of blue traditionally associated with and popularized by Columbia University.
-
A.
Duke blue
Duke blue is the distinctive deep royal blue shade associated with Duke University’s branding and athletic teams.
-
B.
Yale Blue
Yale Blue is a deep, rich shade of blue traditionally associated with academic institutions and collegiate branding.
-
C.
Berkeley Blue
Berkeley Blue is a deep navy shade that serves as one of the primary official colors representing the University of California, Berkeley.
-
D.
Oxford blue
Oxford blue is a dark, rich shade of navy traditionally associated with the University of Oxford and its sports teams.
-
E.
the Blue
The Blue is the traditional nickname and spirit symbol representing Phillips Academy Andover’s athletic teams and school community.
- 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_69a4938b04208190b82e1df6b572c548 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac09249c8190a8099b94a3c9e2cc |
completed | March 1, 2026, 9:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7929c8c9c8190a0279f347ab64765 |
completed | March 4, 2026, 2:02 a.m. |
| NEDg | Description generation | batch_69a792fcb75881908562b79005d62b3b |
completed | March 4, 2026, 2:03 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a793fd988481908ad3c6d2cd46026d |
completed | March 4, 2026, 2:07 a.m. |
Created at: March 1, 2026, 7:38 p.m.