Triple
T29138122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mr. Crocker |
E738557
|
entity |
| Predicate | lostFairyGodparentsOn |
P166360
|
FINISHED |
| Object | Fairy-take-away day |
—
|
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: Fairy-take-away day | Statement: [Mr. Crocker, lostFairyGodparentsOn, Fairy-take-away day]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lostFairyGodparentsOn Context triple: [Mr. Crocker, lostFairyGodparentsOn, Fairy-take-away day]
-
A.
hasFairyGodparent
Indicates that one entity serves as a fairy godparent to another, providing magical guardianship or assistance.
-
B.
lostAfterDiscovery
Indicates that something ceased to be possessed or went missing after it had already been found or discovered.
-
C.
lostIn
Indicates that an entity has become unable to find its way or is no longer in control or possession within a particular place, situation, or context.
-
D.
lostWith
Indicates that one entity experienced a loss or defeat in conjunction with, or as part of the same side/team as, another entity.
-
E.
lostTo
Indicates that one entity was defeated by another in a competition, conflict, or comparison.
- F. None of above. chosen
Provenance (4 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_69f07cb3adb48190a9e0e169cd026634 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f6626d07e48190903642d4553fdae2 |
completed | May 2, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
| PDg | Predicate description generation | batch_69f65f75ac608190a62cd6afce14f68e |
completed | May 2, 2026, 8:32 p.m. |
Created at: April 28, 2026, 11:35 a.m.