Triple
T20086945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tita |
E496159
|
entity |
| Predicate | emotionTransmissionMedium |
P77530
|
FINISHED |
| Object | dishes she cooks |
—
|
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: dishes she cooks | Statement: [Tita, emotionTransmissionMedium, dishes she cooks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: emotionTransmissionMedium Context triple: [Tita, emotionTransmissionMedium, dishes she cooks]
-
A.
mediumOfCommunicationFor
Indicates that one entity serves as the medium or channel through which another entity communicates or conveys information.
-
B.
commonMedium
Indicates that two or more entities share the same medium or channel through which interaction, communication, or transmission occurs.
-
C.
textualTransmission
Indicates the transfer or communication of information through written or printed text from one source to another.
-
D.
languageOfTransmission
Indicates the language used to convey or transmit the content or information in a given communication or resource.
-
E.
propagationMedium
chosen
Indicates the medium or substance through which something (such as a signal, wave, or influence) is transmitted or propagated.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655ba40c8190adea0e271a1249cf |
completed | April 20, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:12 p.m.