Triple
T34021150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gāhā Sattasaī |
E872384
|
entity |
| Predicate | typicalSpeakerInPoems |
P200700
|
FINISHED |
| Object | women |
—
|
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: women | Statement: [Gāhā Sattasaī, typicalSpeakerInPoems, women]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalSpeakerInPoems Context triple: [Gāhā Sattasaī, typicalSpeakerInPoems, women]
-
A.
typicalSpeaker
Indicates that the subject is a prototypical or characteristic speaker or source of utterances in the context of the object.
-
B.
typicalSpeakersAre
chosen
Indicates that the entities specified are the kinds of speakers who typically use or produce the expression or language in question.
-
C.
hasPoeticSpeaker
Indicates that one entity functions as the poetic speaker or voice expressing the content of another entity (such as a poem or lyrical work).
-
D.
characterizesPoetAs
Indicates that one entity portrays, defines, or describes a poet in terms of particular qualities, roles, or attributes.
-
E.
favoritePoet
Indicates that one entity is the poet whom another entity prefers above all other poets.
- 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_69f349a19ad88190ab586f010c804a8f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379f963908190846d232f386fd98f |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:51 a.m.