Triple
T35138141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Arrow |
E1014627
|
entity |
| Predicate | sidekickRealName |
P182323
|
FINISHED |
| Object | Roy Harper |
—
|
NE NERFINISHED |
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: Roy Harper | Statement: [Green Arrow, sidekickRealName, Roy Harper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sidekickRealName Context triple: [Green Arrow, sidekickRealName, Roy Harper]
-
A.
formerSidekick
Indicates that one entity previously served as a sidekick or subordinate companion to another entity, but no longer holds that role.
-
B.
supportingCharacter
Indicates that one entity plays a secondary or assisting role in the story or context relative to another primary entity.
-
C.
leadCharacterNickname
Indicates that one entity is the nickname commonly used for the lead (main) character of another entity.
-
D.
usesSidekick
Indicates that one entity regularly relies on or employs another entity as a supporting assistant or secondary helper in its activities.
-
E.
supportingCharacterPortrayedBy
Indicates that a supporting (non-leading) character in a work is portrayed or acted by a specific performer.
- F. None of above. chosen
Provenance (4 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_69f76dd9c1848190af70d4882a2c1ad7 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78ce78b508190955848e133398dc8 |
completed | May 3, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69f78b9106008190930b3b3675b737d6 |
completed | May 3, 2026, 5:53 p.m. |
| PDg | Predicate description generation | batch_69f78c337cec8190bfdab225a3cc96db |
completed | May 3, 2026, 5:56 p.m. |
Created at: May 3, 2026, 4:02 p.m.