Triple
T5029685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jimmy Hoffa |
E113264
|
entity |
| Predicate | disappearedWhile |
P47888
|
FINISHED |
| Object | waiting for a meeting at the Machus Red Fox restaurant |
—
|
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: waiting for a meeting at the Machus Red Fox restaurant | Statement: [Jimmy Hoffa, disappearedWhile, waiting for a meeting at the Machus Red Fox restaurant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disappearedWhile Context triple: [Jimmy Hoffa, disappearedWhile, waiting for a meeting at the Machus Red Fox restaurant]
-
A.
disappearedDuring
chosen
Indicates that an entity ceased to be observable or present during the time span or event associated with another entity.
-
B.
disappearedWhileSearchingFor
Indicates that one entity vanished or went missing in the course of actively searching for another entity.
-
C.
placeOfDisappearance
Indicates the location where an entity was last seen or went missing.
-
D.
disappearance
Indicates that an entity ceases to be present, visible, or detectable in a given context or location.
-
E.
disappearanceFromSources
Indicates that an entity ceases to be mentioned or recorded in the available sources after a certain point in time.
- 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_69bd443775e48190a646ffbfc4334723 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd739099a0819099c6201d4e1c5ee2 |
completed | March 20, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69bd71509e9c8190a60c1d8d04936a12 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:36 p.m.