Triple
T32561707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernhardts |
E832244
|
entity |
| Predicate | hasPossessiveFormOf |
P119622
|
FINISHED |
| Object | Bernhardt |
—
|
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: Bernhardt | Statement: [Bernhardts, hasPossessiveFormOf, Bernhardt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPossessiveFormOf Context triple: [Bernhardts, hasPossessiveFormOf, Bernhardt]
-
A.
hasPossessiveAffixes
chosen
Indicates that an entity (typically a word or morpheme) carries affixes that mark grammatical possession or ownership.
-
B.
hasPositiveForm
Indicates that one form, variant, or expression is the positive (non-comparative, non-superlative, or affirmative) version of another.
-
C.
hasAdjectiveForm
Indicates that one term is the adjective form derived from another related term (such as a noun or verb).
-
D.
hasCaseForms
Indicates that an entity possesses multiple grammatical case variants or inflected forms associated with it.
-
E.
hasNeuterForm
Indicates that an entity has a grammatical form specifically used for neuter gender.
- 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_69f34926b9848190ace47d2dd0a0de7c |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69feb5e66224819083b87c3707a5a5e0 |
completed | May 9, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69feb3bd700c8190991ed200cd3c04db |
completed | May 9, 2026, 4:10 a.m. |
Created at: May 1, 2026, 1:03 a.m.