Triple
T17005336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Story of My Life |
E412554
|
entity |
| Predicate | part1Content |
P34767
|
FINISHED |
| Object | Helen Keller’s life up to age 21 written by herself |
—
|
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: Helen Keller’s life up to age 21 written by herself | Statement: [The Story of My Life, part1Content, Helen Keller’s life up to age 21 written by herself]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: part1Content Context triple: [The Story of My Life, part1Content, Helen Keller’s life up to age 21 written by herself]
-
A.
articleContent
chosen
Indicates that one entity is the textual or media content that makes up the body of another entity, typically an article or document.
-
B.
module2Content
Indicates that one entity contains or provides the instructional or informational material that makes up the second module in a sequence or course.
-
C.
firstPartTitle
Indicates that one entity is the first part or initial segment of the title of another entity.
-
D.
article2Content
Indicates that one article serves as the content or body text for another article or higher-level publication entity.
-
E.
article1ContentSummary
Indicates a brief, condensed representation of the main points or key information contained in the first article’s content.
- 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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d382400c819092ec0ca0de815888 |
completed | April 18, 2026, 6:54 p.m. |
| PD | Predicate disambiguation | batch_69e35d552bc08190af17ef7659e094ef |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:32 a.m.