Triple
T37374346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Little Big Man |
E927933
|
entity |
| Predicate | followsCharacterLifeFrom |
P43852
|
FINISHED |
| Object | childhood |
—
|
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: childhood | Statement: [Little Big Man, followsCharacterLifeFrom, childhood]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsCharacterLifeFrom Context triple: [Little Big Man, followsCharacterLifeFrom, childhood]
-
A.
followsCharacterFrom
Indicates that one character moves or proceeds behind another character, maintaining a trailing or pursuing position relative to them.
-
B.
followsCharactersFrom
Indicates that one entity continues or tracks the narrative, actions, or developments involving specific characters from another entity.
-
C.
followsCharacterTo
Indicates that one character moves after or in pursuit of another character to a particular location or destination.
-
D.
followsCharacter
Indicates that one character moves or acts after another character, maintaining a trailing or subsequent position or sequence relative to them.
-
E.
followsLifeOf
chosen
Indicates that one entity’s narrative, development, or progression is tracked or depicted over the course of that entity’s life.
- 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_69f76eb820248190a5c395ca50ad002a |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff6a4ce9a08190b98abde3a170dd69 |
completed | May 9, 2026, 5:09 p.m. |
| PD | Predicate disambiguation | batch_69ff69c11634819089d1084bd2c11534 |
completed | May 9, 2026, 5:07 p.m. |
Created at: May 3, 2026, 4:16 p.m.