Triple
T34936446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | About Alice |
E1007584
|
entity |
| Predicate | hasNotableReview |
P175658
|
FINISHED |
| Object | praised for warmth and humor |
—
|
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: praised for warmth and humor | Statement: [About Alice, hasNotableReview, praised for warmth and humor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableReview Context triple: [About Alice, hasNotableReview, praised for warmth and humor]
-
A.
hasNotableCritic
Indicates that one entity serves as a significant or widely recognized critic of another entity.
-
B.
hasRecension
Indicates that one textual version or edition is a revised or alternative form of another text.
-
C.
hasBeenReviewedIn
chosen
Indicates that an entity has been evaluated or critiqued within a specific review, publication, or reviewing context.
-
D.
oftenReviewedBy
Indicates that an entity frequently receives reviews or evaluations from a particular reviewer or group of reviewers.
-
E.
hasNotableResponse
Indicates that an entity has received a significant, noteworthy, or widely recognized reaction or feedback in response to it.
- 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_69f76dc513fc819084a1ff52abbfa5bc |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a035052a47081908e9e56e21c543d46 |
completed | May 12, 2026, 4:07 p.m. |
| PD | Predicate disambiguation | batch_6a034d306e588190a2dce906fd46eb54 |
completed | May 12, 2026, 3:54 p.m. |
Created at: May 3, 2026, 4 p.m.