Triple
T1123375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sirens |
E24661
|
entity |
| Predicate | laterBodyForm |
P17596
|
FINISHED |
| Object | part woman, part fish in later Western tradition |
—
|
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: part woman, part fish in later Western tradition | Statement: [Sirens, laterBodyForm, part woman, part fish in later Western tradition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterBodyForm Context triple: [Sirens, laterBodyForm, part woman, part fish in later Western tradition]
-
A.
subsequentForm
chosen
Indicates that one form, version, or state of something occurs later in sequence or development than another.
-
B.
associatedBody
Indicates a relationship where one entity is linked or connected to another entity as its related or corresponding body.
-
C.
publicBody
Indicates that an entity functions as a governmental or publicly controlled organization that performs public duties or services.
-
D.
createdBody
Indicates that one entity brought another entity into existence or produced it as a result of its actions.
-
E.
body
Indicates that one entity is the physical body or main corporeal form of another entity.
- 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_69a4940712c88190aa244f3fc6070a65 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bc4bc21881909dcfe628f59f3e8c |
completed | March 1, 2026, 10:23 p.m. |
| PD | Predicate disambiguation | batch_69a4bb4749ac8190b0fbddac2e9b2586 |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:44 p.m.