Triple
T20702028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christopher McCandless |
E508806
|
entity |
| Predicate | usedAsShelter |
P101706
|
FINISHED |
| Object | abandoned bus on the Stampede Trail |
—
|
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: abandoned bus on the Stampede Trail | Statement: [Christopher McCandless, usedAsShelter, abandoned bus on the Stampede Trail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsShelter Context triple: [Christopher McCandless, usedAsShelter, abandoned bus on the Stampede Trail]
-
A.
areaServedAsShelterFor
Indicates that one entity functioned as a shelter or refuge for another entity, providing protection or a safe place.
-
B.
takenAsRefugeBy
chosen
Indicates that one entity is used or relied upon by another entity as a place or source of safety, protection, or refuge.
-
C.
hasShelters
Indicates that one entity provides, contains, or is associated with one or more shelters for another entity or purpose.
-
D.
relativeShelterFrom
Indicates that one entity provides shelter or protection for another entity relative to some reference condition, location, or alternative.
-
E.
hadSanctuaryOf
Indicates that an entity possessed or hosted a sanctuary dedicated to another entity.
- 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_69e0b4c2b2a481909e31e9cb8f81ab55 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c18cb9cc819095d0669dca037424 |
completed | April 21, 2026, 12:15 a.m. |
| PD | Predicate disambiguation | batch_69e5c044d1108190b2b5d25de23f6401 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:12 p.m.