Triple
T10607392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dustin Hoffman as Harold Meyerowitz |
E275909
|
entity |
| Predicate | characterArtForm |
P94898
|
FINISHED |
| Object | sculpture |
—
|
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: sculpture | Statement: [Dustin Hoffman as Harold Meyerowitz, characterArtForm, sculpture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterArtForm Context triple: [Dustin Hoffman as Harold Meyerowitz, characterArtForm, sculpture]
-
A.
characterForm
Indicates that one entity is a particular form, version, or transformation state of a character.
-
B.
characterDesigner
Indicates a relationship where an entity is responsible for designing or creating the visual or conceptual characteristics of a character.
-
C.
character3
Indicates a tertiary or additional character role associated with an entity, typically the third distinct character linked within a given context or work.
-
D.
character2
Indicates that a second character entity is involved in the relationship or context defined by the predicate.
-
E.
artisticCharacteristic
Indicates that one entity possesses or exhibits a particular artistic quality, style, or trait in relation to another.
- 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_69d6aaf948d88190806cc3a8c47a3fb2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d6df4c38c881908f69bb757b8e03f5 |
completed | April 8, 2026, 11:05 p.m. |
| PD | Predicate disambiguation | batch_69d6dd72c1288190adbb5e79e94c044a |
completed | April 8, 2026, 10:57 p.m. |
| PDg | Predicate description generation | batch_69d6df463ea8819091d6683e476b4f21 |
completed | April 8, 2026, 11:05 p.m. |
Created at: April 8, 2026, 7:32 p.m.