Triple
T27784746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RLG |
E700930
|
entity |
| Predicate | hasCapitalizationFocus |
P171432
|
FINISHED |
| Object | large-cap |
—
|
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: large-cap | Statement: [RLG, hasCapitalizationFocus, large-cap]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCapitalizationFocus Context triple: [RLG, hasCapitalizationFocus, large-cap]
-
A.
hasCharacterFocus
Indicates that a work, scene, or segment centers primarily on a particular character’s experiences, perspective, or development.
-
B.
capitalizationFocus
chosen
Indicates a relationship where attention or emphasis is placed on the use, style, or correctness of capitalization in text.
-
C.
hasFocusText
Indicates that one entity provides the primary or highlighted textual content associated with another entity.
-
D.
hasCompositionalFocus
Indicates that one entity is the primary subject or focal element within the compositional structure of another entity.
-
E.
hadFocus
Indicates that an entity previously possessed or maintained primary attention, emphasis, or priority within a given context or interaction.
- 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_69ef6a50d8088190acbf3dfbb06d8091 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f7be53890081909b1d93f30a8f31c6 |
completed | May 3, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69f7bccacbac8190978976324c67db28 |
completed | May 3, 2026, 9:23 p.m. |
Created at: April 27, 2026, 5:24 p.m.