Triple
T38389622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pygmalion myth |
E899676
|
entity |
| Predicate | hasMediumOfKeySource |
P7961
|
FINISHED |
| Object | epic poetry |
—
|
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: epic poetry | Statement: [Pygmalion myth, hasMediumOfKeySource, epic poetry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMediumOfKeySource Context triple: [Pygmalion myth, hasMediumOfKeySource, epic poetry]
-
A.
hasKeyMedium
Indicates that one entity possesses or is associated with a key that serves as a medium or intermediary for access, control, or communication with another entity.
-
B.
hasAssociatedMedium
chosen
Indicates that one entity is linked to another entity that serves as its medium, format, or channel of expression or transmission.
-
C.
hasIntendedMedium
Indicates that an entity is associated with a medium or format it is designed, planned, or meant to be presented or communicated through.
-
D.
hasMobileKey
Indicates that an entity possesses or is associated with a mobile-based digital key used for access or authentication.
-
E.
hasSecondarySource
Indicates that an entity is supported, documented, or referenced by a secondary source rather than by a primary or original source.
- 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_69f76e5c9b808190b486523f5c2f817d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffc083a54c8190ac80d05ee8d20a6b |
completed | May 9, 2026, 11:17 p.m. |
| PD | Predicate disambiguation | batch_69ffbfeb05b88190b4d50ce8124004d9 |
completed | May 9, 2026, 11:14 p.m. |
Created at: May 3, 2026, 4:31 p.m.