Triple
T35943398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irene Dunne as Helen Lawrence |
E1039516
|
entity |
| Predicate | starsOpposite |
P184920
|
FINISHED |
| Object | Charles Boyer as Philip Andre Chagal |
—
|
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: Charles Boyer as Philip Andre Chagal | Statement: [Irene Dunne as Helen Lawrence, starsOpposite, Charles Boyer as Philip Andre Chagal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: starsOpposite Context triple: [Irene Dunne as Helen Lawrence, starsOpposite, Charles Boyer as Philip Andre Chagal]
-
A.
starIs
Indicates that one entity is identified or classified as a star in relation to another entity or context.
-
B.
stars
Indicates that one entity marks, highlights, or designates another as special, important, or featured (often by assigning a star or similar marker).
-
C.
starsPosition
Indicates that one entity specifies the spatial location or coordinates of a star or group of stars relative to a reference frame.
-
D.
starsAsBestFriend
Indicates that one entity plays the role of the best friend of another entity in a starring or primary capacity.
-
E.
starPosition
Indicates the spatial location or coordinates of a star relative to a defined reference frame.
- 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_69f76e24bbd0819096b837d35371639a |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7b69b333081909cadbed3fcb8ecf5 |
completed | May 3, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c2a5f8819094ad4621d7b97e0c |
completed | May 3, 2026, 8:49 p.m. |
| PDg | Predicate description generation | batch_69f7b69a74a08190b31b1201278a2c57 |
completed | May 3, 2026, 8:56 p.m. |
Created at: May 3, 2026, 4:07 p.m.