Triple
T30902628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Short Song Style |
E787211
|
entity |
| Predicate | usesAllusionTo |
P102154
|
FINISHED |
| Object | Zhou Gong (Duke of Zhou) |
—
|
NE NERFINISHED |
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: Zhou Gong (Duke of Zhou) | Statement: [Short Song Style, usesAllusionTo, Zhou Gong (Duke of Zhou)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesAllusionTo Context triple: [Short Song Style, usesAllusionTo, Zhou Gong (Duke of Zhou)]
-
A.
containsAllusion
chosen
Indicates that one entity includes or incorporates an indirect reference or allusion to another entity.
-
B.
nameAllusion
Indicates that one entity’s name is derived from, references, or alludes to another entity.
-
C.
alludesToAuthor
Indicates that one entity indirectly references, hints at, or makes an oblique mention of an author as its subject.
-
D.
titleAlludesTo
Indicates that one title makes an indirect or suggestive reference to the content, theme, or another work associated with the other.
-
E.
mottoAllusion
Indicates that a motto references, echoes, or alludes to another work, idea, phrase, or 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_69f224bcbcb48190836df847424e4057 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6f8565134819096aac0175f924a9f |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
Created at: April 29, 2026, 8:50 p.m.