Triple
T33935618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On Kawara telegram works |
E870021
|
entity |
| Predicate | hasMainText |
P7166
|
FINISHED |
| Object | I AM STILL ALIVE |
—
|
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: I AM STILL ALIVE | Statement: [On Kawara telegram works, hasMainText, I AM STILL ALIVE]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainText Context triple: [On Kawara telegram works, hasMainText, I AM STILL ALIVE]
-
A.
hasMainBody
Indicates that one entity serves as the primary physical or structural body of another entity.
-
B.
hasText
chosen
Indicates that an entity is associated with or contains a specific piece of textual content.
-
C.
numberOfMainTexts
Indicates the quantity of primary or main textual components associated with an entity.
-
D.
hasTextIn
Indicates that an entity contains or is associated with a specific piece of text within a particular context or location.
-
E.
hasMainTitleCue
Indicates that an entity is associated with a primary or main title cue used for identification or display.
- 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_69f3499a59788190bff762a891471b31 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a014a0b57dc8190b04ce51156ab95fa |
completed | May 11, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_6a0149afa57c8190a83257085766d916 |
completed | May 11, 2026, 3:14 a.m. |
Created at: May 1, 2026, 1:49 a.m.