Triple
T29347070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The White Knight |
E744198
|
entity |
| Predicate | farewells |
P123681
|
FINISHED |
| Object | Alice at the last brook before she becomes a queen |
—
|
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: Alice at the last brook before she becomes a queen | Statement: [The White Knight, farewells, Alice at the last brook before she becomes a queen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: farewells Context triple: [The White Knight, farewells, Alice at the last brook before she becomes a queen]
-
A.
farewellTour
Indicates that an entity is undertaking a final series of appearances, performances, or visits intended to mark its retirement or conclusion.
-
B.
awayFrom
Indicates that one entity is located at a distance from, or moving farther away from, another entity.
-
C.
closingGreeting
chosen
Indicates the relationship where one party delivers a final, polite or friendly remark to conclude an interaction or communication.
-
D.
regards
Indicates that one entity considers, views, or treats another entity in a particular way or with a certain attitude.
-
E.
faregates
Indicates a relationship where entities are associated with or pass through fare control gates, typically used to regulate and record entry or exit in a transit system.
- 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_69f0a79a2d748190bc30abd469298b37 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f6695868ec8190acc362e10b252ace |
completed | May 2, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69f660f4f7a88190b93c60d76b86c912 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 2:03 p.m.