Triple
T16146849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cindy Lou Who |
E391805
|
entity |
| Predicate | ageInOriginalBook |
P67527
|
FINISHED |
| Object | two years old |
—
|
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: two years old | Statement: [Cindy Lou Who, ageInOriginalBook, two years old]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageInOriginalBook Context triple: [Cindy Lou Who, ageInOriginalBook, two years old]
-
A.
lastOriginalEditionYear
Indicates the calendar year in which the work’s most recent original (non-revised) edition was first published.
-
B.
ageInSeries
Indicates the age of an entity as it appears or is depicted within a specific series or installment of a work.
-
C.
appearsInBookNumber
Indicates that an entity is featured or mentioned in a specific book identified by its number within a series or collection.
-
D.
ageDuringNarration
chosen
Indicates that an entity has a specified age at the time when the described narrative or event is taking place.
-
E.
correctedEditionYear
Indicates the year in which a corrected or revised edition of a work was published or released.
- 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_69d87f1c65e48190aa2b4c472e9bafc4 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21d947e68819081b4b7c757ce71b6 |
completed | April 17, 2026, 11:46 a.m. |
| PD | Predicate disambiguation | batch_69e182885bc08190822ae7e8a4b8ac1f |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5:01 a.m.