Triple
T11669803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Abraham Erskine |
E277347
|
entity |
| Predicate | realName |
P9233
|
FINISHED |
| Object | Abraham Erskine |
E277347
|
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: Abraham Erskine | Statement: [Dr. Abraham Erskine, realName, Abraham Erskine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abraham Erskine Context triple: [Dr. Abraham Erskine, realName, Abraham Erskine]
-
A.
Dr. Abraham Erskine
chosen
Dr. Abraham Erskine is a brilliant scientist in the Marvel universe best known for creating the Super-Soldier Serum that transformed Steve Rogers into Captain America.
-
B.
Albert Stark
Albert Stark is the timid, unlucky sheep farmer protagonist of the comedy Western film "A Million Ways to Die in the West," portrayed by Seth MacFarlane.
-
C.
Howard Stark
Howard Stark is a brilliant industrialist, inventor, and co-founder of S.H.I.E.L.D. in the Marvel universe, known for shaping advanced technology and influencing his son Tony Stark’s legacy.
-
D.
Joe Simmons
Joe Simmons is the son of American actor J.K. Simmons.
-
E.
Martin Stein
Martin Stein is a brilliant nuclear physicist and one half of the superhero Firestorm in the DC Comics universe and its television adaptations.
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a44264c08190ba1a4a5bcdc9367b |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f0191ced188190b79de079b6890221 |
completed | April 28, 2026, 2:19 a.m. |
Created at: April 8, 2026, 9:39 p.m.