Triple
T8516233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ken Seng |
E201578
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | Obsessed |
E738879
|
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: Obsessed | Statement: [Ken Seng, workedOn, Obsessed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Obsessed Context triple: [Ken Seng, workedOn, Obsessed]
-
A.
Obsessed
chosen
Obsessed is a work by creator Ken Seng, recognized as one of his notable contributions to his field.
-
B.
Obsessed
Obsessed is a 2009 psychological thriller film starring Idris Elba, Beyoncé, and Ali Larter about a successful executive whose life unravels when a temp employee becomes dangerously fixated on him.
-
C.
Obsessed
Obsessed is a social media account or online persona that is followed by the user Cinco.
-
D.
Obsessed
"Obsessed" is a country-pop studio album by American duo Dan + Shay, featuring romantic, harmony-rich tracks that helped solidify their mainstream success.
-
E.
Obsessed
"Obsessed" is a crime thriller novel in the Michael Bennett series by James Patterson, following the NYPD detective as he tackles a particularly personal and dangerous case.
- 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_69ca8321bb44819081b74df0b710276d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe60f37b0819082ae14e539f57b56 |
completed | March 31, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce6d37df3081909d8d38363b8d2304 |
completed | April 2, 2026, 1:20 p.m. |
Created at: March 30, 2026, 6:15 p.m.