Triple
T748115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard Crimson men’s tennis |
E15387
|
entity |
| Predicate | sponsorLevel |
P18731
|
FINISHED |
| Object | varsity |
—
|
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: varsity | Statement: [Harvard Crimson men’s tennis, sponsorLevel, varsity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sponsorLevel Context triple: [Harvard Crimson men’s tennis, sponsorLevel, varsity]
-
A.
sponsorType
Indicates the specific role or category of sponsorship that an entity provides in relation to another entity or event.
-
B.
designationLevel
Indicates the specific rank, tier, or level assigned to an entity within a designation or classification system.
-
C.
honorLevel
Indicates the degree or status of respect, distinction, or recognition accorded to an entity relative to others.
-
D.
stateOfSponsor
Indicates the current status or condition of a sponsor in relation to the sponsored entity or activity.
-
E.
sponsorInHouse
Indicates that one entity formally supports, promotes, or funds another entity within the same organization, institution, or internal setting.
- 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_69a49358aa308190adbc9b5a0a2adcf9 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a62f31888190b80cb0a7220f8d80 |
completed | March 1, 2026, 8:48 p.m. |
| PD | Predicate disambiguation | batch_69a4a5004f708190a984ee221716e19c |
completed | March 1, 2026, 8:43 p.m. |
| PDg | Predicate description generation | batch_69a4a58c0a84819094f07658dc651b36 |
completed | March 1, 2026, 8:46 p.m. |
Created at: March 1, 2026, 7:37 p.m.