Triple
T30294485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lew Moran |
E770478
|
entity |
| Predicate | strandedAfter |
P169054
|
FINISHED |
| Object | plane crash in the desert |
—
|
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: plane crash in the desert | Statement: [Lew Moran, strandedAfter, plane crash in the desert]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: strandedAfter Context triple: [Lew Moran, strandedAfter, plane crash in the desert]
-
A.
strandedIn
Indicates that an entity is left isolated or stuck in a particular place or situation without the means to leave or resolve it.
-
B.
strandedWith
Indicates that one entity is stuck or left without means to leave in the company or presence of another entity.
-
C.
strandedLocationType
Indicates the type or category of place where an entity is stranded.
-
D.
isAbandonedAtSeaBy
Indicates that one entity is deliberately left behind or deserted at sea by another entity.
-
E.
beachedAt
Indicates that something has come ashore and is stranded or resting on a beach at a particular location or time.
- F. None of above. chosen
Provenance (4 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_69f224875c288190a9b96b975006ec4a |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68135f7a48190ba5bb6a59815647c |
completed | May 2, 2026, 10:56 p.m. |
| PD | Predicate disambiguation | batch_69f6760216108190bbb708d53a6c2c25 |
completed | May 2, 2026, 10:09 p.m. |
| PDg | Predicate description generation | batch_69f676c35f3481909b9ba18a5662d6ce |
completed | May 2, 2026, 10:12 p.m. |
Created at: April 29, 2026, 7:47 p.m.