Triple
T3139555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ryan Reynolds |
E65610
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Green Lantern |
E101339
|
NE 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: Green Lantern | Statement: [Ryan Reynolds, notableWork, Green Lantern]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Green Lantern Context triple: [Ryan Reynolds, notableWork, Green Lantern]
-
A.
Green Lantern
chosen
Green Lantern is a long-running DC Comics superhero franchise centered on intergalactic peacekeepers who wield power rings fueled by willpower.
-
B.
Mister Miracle
Mister Miracle is a DC Comics superhero and master escape artist created by Jack Kirby as part of his Fourth World saga.
-
C.
The Peacemaker
The Peacemaker is the legendary spiritual leader credited with uniting the Haudenosaunee (Iroquois) nations under the Great Law of Peace.
-
D.
Legion
"Legion" is a 2010 supernatural action-horror film in which archangel Michael defies God to protect humanity from an impending apocalypse.
-
E.
The Flash
The Flash is a professional women's soccer team based in Western New York that has competed in top-tier U.S. leagues.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad8582f564819088c27e1f96153938 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada57743e08190a1069c62e32f1bd4 |
completed | March 8, 2026, 4:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b224e11c508190b69c16dfb5313fc2 |
completed | March 12, 2026, 2:28 a.m. |
Created at: March 8, 2026, 3:05 p.m.