Triple
T9723337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evelyn Abbott |
E235536
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Marcus Abbott |
E161009
|
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: Marcus Abbott | Statement: [Evelyn Abbott, child, Marcus Abbott]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcus Abbott Context triple: [Evelyn Abbott, child, Marcus Abbott]
-
A.
Marcus Abbott
chosen
Marcus Abbott is a central character in the horror film series "A Quiet Place," known as the son in the Abbott family who must survive in a world overrun by sound-sensitive creatures.
-
B.
Adam Biddle
Adam Biddle is a British cinematographer known for his dynamic, high-energy visual style in action films such as "Crank."
-
C.
Grant Bardsley
Grant Bardsley is a British voice actor best known for voicing the protagonist Taran in Disney’s animated film "The Black Cauldron."
-
D.
Brian Routh
Brian Routh was a British performance artist and musician best known as one half of the avant-garde comedy and performance duo The Kipper Kids.
-
E.
Garrett Cotter
Garrett Cotter was an Irish-born convict and early settler in Australia after whom the Cotter River in the Australian Capital Territory is named.
- 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_69ca84d0123c819096f9dc3b6abb0881 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e75abd48190a6e6679ec51496e8 |
completed | April 1, 2026, 10:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d19fa5a8e48190b7b1742eb6c3b81e |
completed | April 4, 2026, 11:32 p.m. |
Created at: March 30, 2026, 8:20 p.m.