Triple
T36565829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rita Hayworth and Fred Astaire |
E901972
|
entity |
| Predicate | screenChemistryWith |
P110770
|
FINISHED |
| Object | each other |
—
|
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: each other | Statement: [Rita Hayworth and Fred Astaire, screenChemistryWith, each other]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenChemistryWith Context triple: [Rita Hayworth and Fred Astaire, screenChemistryWith, each other]
-
A.
onScreenChemistryWith
Indicates a strong, noticeable dynamic or rapport between two performers when they appear together on screen.
-
B.
hasOnscreenChemistryWith
chosen
Indicates that two entities exhibit a notably engaging or appealing interpersonal dynamic when appearing together on screen.
-
C.
screensOut
Indicates that one entity filters, excludes, or prevents another entity from passing through, being considered, or having an effect.
-
D.
screensAt
Indicates that one entity shows, projects, or displays another entity (such as a film, program, or content) on a screen or at a screening venue.
-
E.
screenWorld
Indicates a relationship where something is displayed, projected, or presented on a screen or within a screen-based environment or world.
- 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_69f76e6416708190a9754b8c52d4e453 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf769338819092a5f42653dcc956 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:11 p.m.