Triple
T16493650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Williams College varsity teams |
E400627
|
entity |
| Predicate | mascot |
P52
|
FINISHED |
| Object |
Ephelia
Ephelia is the purple cow mascot that represents the Williams College varsity athletic teams.
|
E1216405
|
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: Ephelia | Statement: [Williams College varsity teams, mascot, Ephelia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ephelia Context triple: [Williams College varsity teams, mascot, Ephelia]
-
A.
Clelia
Clelia is an Italian feminine given name of Latin origin, historically associated with the legendary Roman heroine Cloelia.
-
B.
Eugeneia
Eugeneia is an alternative spelling or variant form of the given name Eugenia, which is derived from Greek and traditionally associated with nobility or good birth.
-
C.
Galeata
Galeata is a small historic town in Italy’s Emilia-Romagna region, known for its Roman and medieval heritage in the Apennine foothills.
-
D.
Leucothea
Leucothea is a sea goddess in Greek mythology, often associated with aiding shipwrecked sailors and offering divine protection at sea.
-
E.
The Helen
The Helen is a performance space within the Helen Rosenfeld Lewis Bialosky Lab Theatre complex, used for theatrical productions and related arts events.
- 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: Ephelia Triple: [Williams College varsity teams, mascot, Ephelia]
Generated description
Ephelia is the purple cow mascot that represents the Williams College varsity athletic teams.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ephelia Target entity description: Ephelia is the purple cow mascot that represents the Williams College varsity athletic teams.
-
A.
Clelia
Clelia is an Italian feminine given name of Latin origin, historically associated with the legendary Roman heroine Cloelia.
-
B.
Eugeneia
Eugeneia is an alternative spelling or variant form of the given name Eugenia, which is derived from Greek and traditionally associated with nobility or good birth.
-
C.
Galeata
Galeata is a small historic town in Italy’s Emilia-Romagna region, known for its Roman and medieval heritage in the Apennine foothills.
-
D.
Leucothea
Leucothea is a sea goddess in Greek mythology, often associated with aiding shipwrecked sailors and offering divine protection at sea.
-
E.
The Helen
The Helen is a performance space within the Helen Rosenfeld Lewis Bialosky Lab Theatre complex, used for theatrical productions and related arts events.
- 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_69d883813098819084f5409539723b59 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e3189c8819097e6ba62f24b1f6c |
completed | April 18, 2026, 7:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a005828849481909e95c5822ed6f74d |
completed | May 10, 2026, 10:04 a.m. |
| NEDg | Description generation | batch_6a00596390e4819091909806772afa1a |
completed | May 10, 2026, 10:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a005a0baef08190b77423fe81a7a11c |
completed | May 10, 2026, 10:12 a.m. |
Created at: April 10, 2026, 5:13 a.m.