Triple
T23562250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Father and Son |
E579272
|
entity |
| Predicate | vocalPerspective2 |
P120611
|
FINISHED |
| Object | son seeking freedom |
—
|
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: son seeking freedom | Statement: [Father and Son, vocalPerspective2, son seeking freedom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vocalPerspective2 Context triple: [Father and Son, vocalPerspective2, son seeking freedom]
-
A.
hasVocalPerspective
chosen
Indicates that one entity expresses or frames content from the point of view or voice of another entity.
-
B.
vocal
Indicates that an entity produces or is characterized by audible sounds, speech, or vocalizations.
-
C.
vocalForm
Indicates the specific vocal or phonetic form in which something (such as a word, sound, or utterance) is expressed.
-
D.
vocalConfiguration
Indicates how an entity’s vocal or sound-producing characteristics are arranged or specified in relation to another entity or context.
-
E.
vocalTraining
Indicates that one entity provides or engages in training aimed at improving another entity’s vocal or singing abilities.
- 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_69e245fe24588190888f3aec8407d8e3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1af68cddc8190ab9d0b7ee1f157ed |
completed | April 29, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69f118bcc0b08190b25a8dddfd461a0e |
completed | April 28, 2026, 8:29 p.m. |
Created at: April 17, 2026, 6:23 p.m.