Triple
T27488946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Pacific AC-6 |
E693824
|
entity |
| Predicate | classSuccessor |
P10131
|
FINISHED |
| Object | Southern Pacific AC-7 |
—
|
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: Southern Pacific AC-7 | Statement: [Southern Pacific AC-6, classSuccessor, Southern Pacific AC-7]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: classSuccessor Context triple: [Southern Pacific AC-6, classSuccessor, Southern Pacific AC-7]
-
A.
successorFrom
Indicates that one entity directly follows or comes after another in an ordered sequence or progression.
-
B.
successorChild
Indicates that one entity is the child of another entity who is its immediate predecessor or predecessor in a succession or lineage.
-
C.
successorClass
chosen
Indicates that one class directly follows or replaces another class in a sequence or hierarchy.
-
D.
successorOnType
Indicates that one entity directly follows another in an ordered sequence defined by a specific type or category.
-
E.
successorInterface
Indicates that one interface directly follows and replaces another interface in a sequence or version lineage.
- 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f661b58ac48190907b6c6e9ccc2c59 |
completed | May 2, 2026, 8:42 p.m. |
| PD | Predicate disambiguation | batch_69f660eea4648190b0d5e24293607813 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 27, 2026, 1:04 p.m.