Triple
T8668930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marc Jacobs |
E205746
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Jacobs |
E21231
|
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: Jacobs | Statement: [Marc Jacobs, familyName, Jacobs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jacobs Context triple: [Marc Jacobs, familyName, Jacobs]
-
A.
Jacobs
chosen
Jacobs is a surname most notably associated with Harriet Jacobs, the African-American writer and abolitionist who authored the influential slave narrative "Incidents in the Life of a Slave Girl."
-
B.
Jacobsen
Jacobsen is a common Danish surname borne by numerous notable figures in fields such as design, architecture, literature, and politics.
-
C.
Chosen Jacobs
Chosen Jacobs is an American actor and singer best known for his role as Mike Hanlon in the horror film "It" (2017) and its sequel.
-
D.
Jeppson
Jeppson is the maiden surname of American psychiatrist and science fiction writer Janet Asimov.
-
E.
Jacob's
Jacob's is a well-known biscuit brand originating from Ireland, recognized for products like cream crackers and a variety of sweet and savory biscuits.
- 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_69ca83516ae88190aefe034b3bc589e3 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc48a48b548190b78259072b1224ee |
completed | March 31, 2026, 10:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cecd1ca88c8190a3b2ca79a7204248 |
completed | April 2, 2026, 8:10 p.m. |
Created at: March 30, 2026, 6:31 p.m.