Triple
T38622673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Larceny Bourbon |
E936916
|
entity |
| Predicate | replacesRyeWith |
P29646
|
FINISHED |
| Object | wheat |
—
|
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: wheat | Statement: [Larceny Bourbon, replacesRyeWith, wheat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacesRyeWith Context triple: [Larceny Bourbon, replacesRyeWith, wheat]
-
A.
replacedWith
chosen
Indicates that one entity has been substituted or superseded by another entity, taking over its role, function, or position.
-
B.
replacedRide
Indicates that one ride has been substituted for or taken the place of another ride.
-
C.
replacedInQ7By
Indicates that an entity was superseded or substituted by another entity in version or release Q7.
-
D.
replacesInPractice
Indicates that one entity has effectively taken over the role, function, or use of another entity in real-world application or usage.
-
E.
replacement
Indicates that one entity takes the place of, or is substituted for, another entity in a given context.
- 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_69f76ed403208190b862dc795171353f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fec4cffed08190b5e5e7cc0c87493e |
completed | May 9, 2026, 5:23 a.m. |
| PD | Predicate disambiguation | batch_69fec2ea7fe08190bd751b39515f69d1 |
completed | May 9, 2026, 5:15 a.m. |
Created at: May 3, 2026, 4:32 p.m.