Triple
T25874082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | his auld mare Maggie |
E651839
|
entity |
| Predicate | toneOfAddress |
P7344
|
FINISHED |
| Object | affectionate |
—
|
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: affectionate | Statement: [his auld mare Maggie, toneOfAddress, affectionate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: toneOfAddress Context triple: [his auld mare Maggie, toneOfAddress, affectionate]
-
A.
typeOfSpeechDelivered
Indicates that a specific kind or category of speech (e.g., keynote, lecture, toast) was delivered in a given event or context.
-
B.
givesSpeechOn
Indicates that one entity delivers or presents a speech whose topic or subject matter concerns another entity.
-
C.
tone
chosen
Indicates the characteristic attitude or emotional quality expressed in how something is communicated or presented.
-
D.
diplomaticSpeechBy
Indicates that a diplomatic speech or formal address is delivered or authored by a particular agent or entity.
-
E.
roleInAddressing
Indicates the specific function or responsibility an entity has in dealing with or responding to a particular issue, situation, or task.
- 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_69e7ab3ad9d88190841ddcb93ab02e96 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f602df9ae0819080f8d583bde7026e |
completed | May 2, 2026, 1:57 p.m. |
| PD | Predicate disambiguation | batch_69f4939148dc81908706cec7d85291bc |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 8:12 a.m.