Triple
T3171722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Lonely Goatherd |
E66361
|
entity |
| Predicate | hasCharacterMention |
P5716
|
FINISHED |
| Object | goatherd |
—
|
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: goatherd | Statement: [The Lonely Goatherd, hasCharacterMention, goatherd]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCharacterMention Context triple: [The Lonely Goatherd, hasCharacterMention, goatherd]
-
A.
containsCharacter
chosen
Indicates that one entity includes a specific character as part of its content or composition.
-
B.
mentionedAs
Indicates that one entity is referred to or cited by name or description in the context of another entity.
-
C.
usesCharacter
Indicates that one entity employs, incorporates, or relies on a particular character (such as a symbol, letter, or persona) in its form, function, or representation.
-
D.
characterAddressed
Indicates that one character directs speech, communication, or attention specifically toward another character.
-
E.
hasEnigmaticCharacter
Indicates that something possesses a mysterious, puzzling, or difficult-to-interpret quality or nature.
- 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_69ad8585d7988190af37365331093ccd |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada66da23c81908f063b44b48b1e53 |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0076b4819094628f1ad10b8f68 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.