Triple
T30466454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Ballad of Jesse James |
E775153
|
entity |
| Predicate | firstLineVariant |
P197547
|
FINISHED |
| Object | Jesse James was a lad that killed many a man |
—
|
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: Jesse James was a lad that killed many a man | Statement: [The Ballad of Jesse James, firstLineVariant, Jesse James was a lad that killed many a man]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstLineVariant Context triple: [The Ballad of Jesse James, firstLineVariant, Jesse James was a lad that killed many a man]
-
A.
firstVariant
Indicates that the subject is the earliest or primary version among multiple variants of the same entity or item.
-
B.
firstLines
chosen
Indicates that one text, segment, or element constitutes the initial lines or opening portion of another.
-
C.
firstLineForm
Indicates that one entity is the initial or primary line-based representation or form of another entity.
-
D.
firstLineTransition
Indicates a transition or change that occurs at the very first line or initial position in a sequence or text.
-
E.
firstLineOpened
Indicates that the first line of something (e.g., a document, file, or text block) has been opened or accessed.
- 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_69f2249622a48190b1fae2e3e4ee958a |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a0238010fa481909b07a5c22aa0abde |
completed | May 11, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_6a0236cfdcb481908323b67b925c76d9 |
completed | May 11, 2026, 8:06 p.m. |
Created at: April 29, 2026, 8:11 p.m.