Triple
T24848035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the lamplighter |
E621809
|
entity |
| Predicate | perceivedByLittlePrince |
P8789
|
FINISHED |
| Object | admirable |
—
|
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: admirable | Statement: [the lamplighter, perceivedByLittlePrince, admirable]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: perceivedByLittlePrince Context triple: [the lamplighter, perceivedByLittlePrince, admirable]
-
A.
intendedPerception
Indicates that one entity is meant or designed to be perceived (e.g., seen, heard, or otherwise sensed) by another entity.
-
B.
perspectiveOf
chosen
Indicates that something is expressed, depicted, or understood from the viewpoint or standpoint of a particular entity.
-
C.
perceivedByWizardsAs
Indicates that something is regarded or understood in a particular way specifically from the perspective of wizards.
-
D.
exploresPerspectiveOf
Indicates that one entity examines, investigates, or considers the viewpoint, stance, or outlook associated with another entity.
-
E.
La Princesse lointaine
Indicates a distant or unattainable beloved, emphasizing emotional longing and separation rather than physical closeness.
- 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_69e2fac297e481909d3aedc75f585e42 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f453035f508190be83a3d521723acf |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f44d6ef33081908f5d36ba1ae5f473 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 5:20 a.m.