Triple
T35421479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donut Ghost House |
E1023806
|
entity |
| Predicate | exitLeadsTo |
P88382
|
FINISHED |
| Object | Donut Plains 3 |
—
|
NE NERFINISHED |
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: Donut Plains 3 | Statement: [Donut Ghost House, exitLeadsTo, Donut Plains 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exitLeadsTo Context triple: [Donut Ghost House, exitLeadsTo, Donut Plains 3]
-
A.
exitTo
chosen
Indicates that one location or entity serves as a passage or route leading directly to another location or entity.
-
B.
canLeadTo
Indicates that one entity, condition, or event has the potential to cause, result in, or bring about another.
-
C.
exitRoutes
Indicates that there are designated paths or ways for entities to leave or move out from a particular place or situation.
-
D.
declineLeadsTo
Indicates that a decline in one entity or condition results in or causes a subsequent outcome or change in another.
-
E.
hasStepsLeadingTo
Indicates that one location or object is connected to another by a set of steps or a staircase leading toward it.
- 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_69f76df6704081909900c60be10d5849 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7958d59388190a937ac6f4c81d3c9 |
completed | May 3, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69f7910770108190bdd39ddb5d304f54 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:03 p.m.