Triple
T36202747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard–Yale softball rivalry |
E1047310
|
entity |
| Predicate | campus2Location |
P5417
|
FINISHED |
| Object | New Haven, Connecticut |
—
|
NE NERFINISHED |
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: New Haven, Connecticut | Statement: [Harvard–Yale softball rivalry, campus2Location, New Haven, Connecticut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campus2Location Context triple: [Harvard–Yale softball rivalry, campus2Location, New Haven, Connecticut]
-
A.
positionOnCampus
Indicates the spatial location or placement of an entity within the boundaries or layout of a campus.
-
B.
campusDirection
Indicates the relative directional position of one campus location with respect to another.
-
C.
cityCampusServes
Indicates that a city campus provides services, resources, or support to a particular population, area, or institution.
-
D.
campusLandmark
Indicates that something serves as a notable or recognizable landmark located on or associated with a campus.
-
E.
cityCampus
chosen
Indicates that a campus is located within or associated with a particular city.
- F. None of above.
Provenance (3 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_69f76e414bdc8190996f15a544220a3d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7ba6d06f48190a71b5a2f19e2232f |
completed | May 3, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a4aad48190a62e41c5e39339d9 |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:08 p.m.