Triple
T20713575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spanos family |
E509108
|
entity |
| Predicate | primaryBusinessInterest |
P70059
|
FINISHED |
| Object | professional American football |
—
|
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: professional American football | Statement: [Spanos family, primaryBusinessInterest, professional American football]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryBusinessInterest Context triple: [Spanos family, primaryBusinessInterest, professional American football]
-
A.
primaryInterest
Indicates that one entity is the main or most significant focus of attention, concern, or engagement for another entity.
-
B.
primaryBusinessArea
chosen
Indicates the main field, sector, or domain in which an entity primarily conducts its business activities.
-
C.
primaryTrade
Indicates that the referenced activity or exchange is the main or most significant trade relationship associated with the entities involved.
-
D.
subjectInterest
Indicates that the subject has an interest in, or is concerned with, the object.
-
E.
secondaryInterest
Indicates that an entity has a secondary, less primary but still relevant interest or focus in relation to another entity or topic.
- 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_69e0b4c40ad88190b81f77695366d328 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1d001788190a524a17347f9de67 |
completed | April 21, 2026, 12:16 a.m. |
| PD | Predicate disambiguation | batch_69e5c044d1108190b2b5d25de23f6401 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:15 p.m.