Triple
T21776509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keller Dover |
E537596
|
entity |
| Predicate | statusAtEnd |
P64389
|
FINISHED |
| Object | missing and trapped in an underground pit |
—
|
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: missing and trapped in an underground pit | Statement: [Keller Dover, statusAtEnd, missing and trapped in an underground pit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statusAtEnd Context triple: [Keller Dover, statusAtEnd, missing and trapped in an underground pit]
-
A.
statusEndsWhen
Indicates that a particular status or condition ceases to hold when a specified event, time, or state occurs.
-
B.
operationalStatusAtEnd
Indicates the final operational condition or state of an entity at the conclusion of a specified period or process.
-
C.
status
Indicates the current condition, state, or standing of an entity within a given context.
-
D.
statusAtTime
chosen
Indicates that an entity has a particular status or condition at a specified point in time.
-
E.
statusBySeriesEnd
Indicates the condition or outcome of an entity as it stands at the conclusion of a particular series.
- 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_69e0c470759c819094a215757113562b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f046291d808190b5111a8d4819909f |
completed | April 28, 2026, 5:31 a.m. |
| PD | Predicate disambiguation | batch_69e6be6299988190a34c98fa76d94700 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:51 p.m.