Triple
T30031852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ACT college entrance examination |
E763042
|
entity |
| Predicate | optionalSection |
P23744
|
FINISHED |
| Object | Writing |
—
|
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: Writing | Statement: [ACT college entrance examination, optionalSection, Writing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: optionalSection Context triple: [ACT college entrance examination, optionalSection, Writing]
-
A.
extendedSection
Indicates that one section is a continuation or elaborated extension of another section.
-
B.
optionedBy
Indicates that the rights to develop, produce, or exploit something (such as a work, property, or asset) have been contractually secured by a particular party.
-
C.
hasOptionalSection
chosen
Indicates that an entity includes a section or component that is not mandatory and may or may not be present.
-
D.
optionalStage
Indicates that a particular stage in a process, workflow, or sequence is not mandatory and may be included or skipped without invalidating the overall structure.
-
E.
supportsSection
Indicates that one entity provides structural or functional backing or reinforcement to a specific section 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_69f2246fb2b88190acff36bf7975c8f0 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f679afd2a88190856acb9e2d1f87d3 |
completed | May 2, 2026, 10:24 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 6:50 p.m.