Triple
T28957411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jim Norton |
E731199
|
entity |
| Predicate | soberSince |
P166062
|
FINISHED |
| Object | early 1990s (approximate) |
—
|
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: early 1990s (approximate) | Statement: [Jim Norton, soberSince, early 1990s (approximate)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: soberSince Context triple: [Jim Norton, soberSince, early 1990s (approximate)]
-
A.
drunkBy
Indicates that a substance or beverage is consumed by a particular entity.
-
B.
alcoholLevel
Indicates the measured concentration or amount of alcohol present in an entity (such as a person, substance, or environment).
-
C.
drinksAlcohol
Indicates that an entity consumes alcoholic beverages.
-
D.
hasMainAlcoholicBeverage
Indicates that one entity is the primary alcoholic beverage associated with, served by, or featured in another entity.
-
E.
drunkWith
Indicates that one entity is intoxicated as a result of consuming a particular alcoholic beverage or substance associated with another entity.
- 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_69f043eb9bcc819091ac7b07aecb6475 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65bbd8b188190bb8c1a0dbdbbccc6 |
completed | May 2, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
| PDg | Predicate description generation | batch_69f65b136b30819090cf59fb772f35f1 |
completed | May 2, 2026, 8:14 p.m. |
Created at: April 28, 2026, 8:48 a.m.