Triple
T36393814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deadly Desert of Oz |
E896405
|
entity |
| Predicate | effectOnTravelers |
P147857
|
FINISHED |
| Object | destroys anyone who touches it |
—
|
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: destroys anyone who touches it | Statement: [Deadly Desert of Oz, effectOnTravelers, destroys anyone who touches it]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOnTravelers Context triple: [Deadly Desert of Oz, effectOnTravelers, destroys anyone who touches it]
-
A.
affectsTravel
Indicates that one entity has an influence or impact on another entity’s ability, conditions, or patterns of travel.
-
B.
outcomeForTravelers
chosen
Indicates the result or consequence that a travel-related event, decision, or condition has for the travelers involved.
-
C.
travelers
Indicates that one or more entities are engaged in the activity or role of traveling, typically moving from one place to another.
-
D.
basedOnTravel
Indicates that something is determined, derived, or decided according to travel-related factors, conditions, or information.
-
E.
settingOfTravels
Indicates that a location serves as the setting or backdrop for a character’s travels or journey.
- 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_69f76e52e3108190becf70b090ae7bd6 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd91a5dad8819093eeeef527027890 |
completed | May 8, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69fd8f65fe9081908902500a3228d935 |
completed | May 8, 2026, 7:23 a.m. |
Created at: May 3, 2026, 4:10 p.m.