Triple
T14958264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Little Girls |
E372989
|
entity |
| Predicate | targetCharacters |
P83677
|
FINISHED |
| Object | the orphan girls in Annie |
—
|
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: the orphan girls in Annie | Statement: [Little Girls, targetCharacters, the orphan girls in Annie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetCharacters Context triple: [Little Girls, targetCharacters, the orphan girls in Annie]
-
A.
targetsCharacter
Indicates that one entity is the intended focus or target of another entity’s action, effect, or behavior.
-
B.
metCharacter
Indicates that one entity has encountered or been introduced to another entity at least once.
-
C.
targetConstituents
Indicates that a larger entity is directed toward, affects, or is specifically intended for certain constituent parts or members within a whole.
-
D.
character2
Indicates that a second character entity is involved in the relationship or context defined by the predicate.
-
E.
characters
chosen
Indicates that one entity is a character (or set of characters) associated with, appearing in, or belonging to another entity (such as a work, story, or medium).
- 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_69d85cca979481908747d2a81eba1cea |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6cd85bc81909040b7ff78f62554 |
completed | April 15, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69de9a5d995881909e33658f5aea5582 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:40 a.m.