Triple
T9880934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawks (Saint Joseph's men's basketball) |
E180801
|
entity |
| Predicate | mascotCharacteristic |
P91579
|
FINISHED |
| Object | ever-flapping wings |
—
|
LITERAL FINISHED |
How this triple was built (2 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: ever-flapping wings | Statement: [Hawks (Saint Joseph's men's basketball), mascotCharacteristic, ever-flapping wings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mascotCharacteristic Context triple: [Hawks (Saint Joseph's men's basketball), mascotCharacteristic, ever-flapping wings]
-
A.
typeOfMascot
Indicates that one entity is a mascot and specifies the category or kind of mascot it is (e.g., animal, human, object, etc.).
-
B.
mascotTheme
Indicates that an entity serves as the representative mascot associated with a particular theme, concept, or style.
-
C.
hasMascot
Indicates that an entity is represented or symbolized by a particular mascot.
-
D.
isMascot
Indicates that one entity serves as the mascot or symbolic representative for another entity, such as an organization, team, or event.
-
E.
coMascot
Indicates that two entities serve together as mascots for the same organization, event, or group.
- F. None of above. chosen
Provenance (4 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_69ca828082cc8190a40f8d299caa6545 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb41639c88190a9ef3d950485e3ab |
completed | April 2, 2026, 12:11 a.m. |
| PD | Predicate disambiguation | batch_69cd1d810ed48190a252b70e9390c8f3 |
completed | April 1, 2026, 1:28 p.m. |
| PDg | Predicate description generation | batch_69cd36f112bc81908b473787e702de2f |
completed | April 1, 2026, 3:17 p.m. |
Created at: March 30, 2026, 8:38 p.m.