Triple
T27876703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don’t call it a comeback |
E704958
|
entity |
| Predicate | opening lineOf |
P829
|
FINISHED |
| Object | Mama Said Knock You Out |
—
|
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: Mama Said Knock You Out | Statement: [Don’t call it a comeback, opening lineOf, Mama Said Knock You Out]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opening lineOf Context triple: [Don’t call it a comeback, opening lineOf, Mama Said Knock You Out]
-
A.
openingLine
chosen
Indicates that one entity is the first line or initial statement that begins another entity, such as a text, speech, or conversation.
-
B.
openingLineStatus
Indicates the status or condition of an entity’s opening line, such as whether it exists, is valid, or meets a specified criterion.
-
C.
openedFirstLine
Indicates that one entity initiated the opening of something (e.g., a file, document, or interface) before any other entity did, being the first to perform the opening action.
-
D.
originalLineOpened
Indicates that a transportation or service line began its initial operation or was first opened for use.
-
E.
openingDateLineC
Indicates the calendar date on which entity C is opened, initiated, or begins operation.
- 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_69ef84111bb4819084298f994b31c62f |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f67257b0448190a13011af81c81449 |
completed | May 2, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69f66ec3d3d48190ab2f2b71939e572e |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 27, 2026, 6:27 p.m.