Triple
T32135924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lokma |
E820762
|
entity |
| Predicate | canBeGarnishedWith |
P174273
|
FINISHED |
| Object | ground pistachios |
—
|
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: ground pistachios | Statement: [Lokma, canBeGarnishedWith, ground pistachios]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeGarnishedWith Context triple: [Lokma, canBeGarnishedWith, ground pistachios]
-
A.
mayBeGarnishedWith
chosen
Indicates that one item can optionally be used as a garnish or decorative topping for another item.
-
B.
canBeSeizedBy
Indicates that one entity is legally or physically able to be taken control of, captured, or confiscated by another entity.
-
C.
canBeSuedFor
Indicates that one party is legally liable or potentially subject to legal action by another party for a specified cause or wrongdoing.
-
D.
canBeSuedAs
Indicates that one entity has legal standing or capacity to be the target of a lawsuit initiated by another entity.
-
E.
canBeSanctionedFor
Indicates that an entity is subject to penalties or disciplinary measures as a consequence of a specified action, behavior, or condition.
- 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_69f349039e0c819091c7a7d322e3f46d |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fdd92396788190ae1424bc1ae55844 |
completed | May 8, 2026, 12:37 p.m. |
| PD | Predicate disambiguation | batch_69fdd678f40481909a717a2daec83b36 |
completed | May 8, 2026, 12:26 p.m. |
Created at: May 1, 2026, 12:30 a.m.