Triple
T5266444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tony |
E118947
|
entity |
| Predicate | isAssociatedWithTheme |
P20616
|
FINISHED |
| Object | female friendship |
—
|
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: female friendship | Statement: [Tony, isAssociatedWithTheme, female friendship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isAssociatedWithTheme Context triple: [Tony, isAssociatedWithTheme, female friendship]
-
A.
supportsThemeOf
Indicates that one entity reinforces, aligns with, or contributes to the central theme expressed by another entity.
-
B.
hasThemeConnection
chosen
Indicates a relationship where one entity is linked to another through a shared or related theme, topic, or conceptual focus.
-
C.
followsInTheme
Indicates that one element continues or succeeds another while maintaining the same theme or thematic context.
-
D.
themeFor
Indicates that something serves as the central subject, topic, or focus for another thing (such as an event, work, or activity).
-
E.
followsTheme
Indicates that one entity adheres to, is guided by, or is structured according to the theme established by another entity.
- 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_69bd446a42c88190b7ecbef006561d55 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7d5a23908190a24e79d1b29d6fcf |
completed | March 20, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69bd77c71268819094f9f5203eed392d |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:51 p.m.