Triple
T26389918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Coulthard |
E663381
|
entity |
| Predicate | uncleIs |
P8496
|
FINISHED |
| Object | Jim Coulthard |
—
|
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: Jim Coulthard | Statement: [David Coulthard, uncleIs, Jim Coulthard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: uncleIs Context triple: [David Coulthard, uncleIs, Jim Coulthard]
-
A.
uncle
chosen
Indicates a familial relationship where one person is the brother (or brother-in-law) of another person's parent.
-
B.
uncleOrAuntOf
Indicates that one person is the uncle or aunt of another person, typically as the sibling (or sibling-in-law) of the other person’s parent.
-
C.
adoptiveUncle
Indicates a familial relationship where a man is the brother (or brother-in-law) of an adoptive parent of someone, making him that person’s adoptive uncle.
-
D.
halfUncleOf
Indicates a familial relationship where one person is the half-brother of a parent of another person, making him that person's half-uncle.
-
E.
paternalUncleInstanceOf
Indicates that one entity is a specific instance of the paternal uncle relationship to another entity (i.e., the brother of the person's father).
- 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_69ee88374adc81909868f3bab374a32f |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f610be3e848190b7acb7675e37e1f5 |
completed | May 2, 2026, 2:57 p.m. |
| PD | Predicate disambiguation | batch_69f5f800fa9c8190aab0962669fde8ac |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 11:25 p.m.