Triple
T8623135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | mchadi |
E204215
|
entity |
| Predicate | accompanimentRole |
P84498
|
FINISHED |
| Object | used as a bread substitute in Georgian meals |
—
|
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: used as a bread substitute in Georgian meals | Statement: [mchadi, accompanimentRole, used as a bread substitute in Georgian meals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accompanimentRole Context triple: [mchadi, accompanimentRole, used as a bread substitute in Georgian meals]
-
A.
musicalRole
Indicates the specific function or part an entity performs within a musical context, such as in a performance, composition, or ensemble.
-
B.
playsInRole
Indicates that an entity performs or appears in a specific role within a production, event, or context.
-
C.
usuallyAccompaniedBy
Indicates that one entity is commonly or habitually found together with, or occurs in the presence of, another entity.
-
D.
playedAlongside
Indicates that two or more entities participated together at the same time in a shared activity, performance, or event.
-
E.
talentShowRole
Indicates the specific function or position an entity holds within the context of a talent show (e.g., performer, judge, host).
- 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_69ca834a4ea0819094970dceb9e389f3 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5730309081909a9a0256c9bf5f8f |
completed | March 31, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69cc455906f8819082edd79cb4a1cf28 |
completed | March 31, 2026, 10:06 p.m. |
| PDg | Predicate description generation | batch_69cc572d99bc819097f36b140c2ee1ce |
completed | March 31, 2026, 11:22 p.m. |
Created at: March 30, 2026, 6:26 p.m.