Triple
T319258
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philadelphia Eagles–New York Giants rivalry |
E7775
|
entity |
| Predicate | divisionRivalsSince |
P903
|
FINISHED |
| Object | 1970 AFL–NFL merger |
—
|
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: 1970 AFL–NFL merger | Statement: [Philadelphia Eagles–New York Giants rivalry, divisionRivalsSince, 1970 AFL–NFL merger]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: divisionRivalsSince Context triple: [Philadelphia Eagles–New York Giants rivalry, divisionRivalsSince, 1970 AFL–NFL merger]
-
A.
divisionRivalry
chosen
Indicates a competitive or adversarial relationship between entities that belong to the same division or subgroup within a larger organization or system.
-
B.
foundedAsRivalOf
Indicates that an entity was established specifically to compete with or challenge another entity.
-
C.
rivalLeague
Indicates that two leagues are in competition with each other, typically vying for similar audiences, resources, or status.
-
D.
rivalryName
Indicates that a specific name or label is assigned to a rivalry relationship between two entities.
-
E.
hasRivalryAspect
Indicates that there exists a competitive or adversarial relationship or dimension between entities.
- 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_69a2e7e7af7881908890039d6be4e9b8 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eb7df63c8190b7cd1bcfdfd96187 |
completed | Feb. 28, 2026, 1:19 p.m. |
| PD | Predicate disambiguation | batch_69a2e94513ec819089f5177f7a521e65 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.