Triple
T1955665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emma Thomas |
E42261
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Following |
E47434
|
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: Following | Statement: [Emma Thomas, notableWork, Following]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Following Context triple: [Emma Thomas, notableWork, Following]
-
A.
Following
chosen
Following is Christopher Nolan's 1998 low-budget neo-noir thriller feature debut, known for its nonlinear narrative and exploration of voyeurism and identity.
-
B.
Of Followers and Friends
"Of Followers and Friends" is a reflective essay exploring the nature of social relationships, loyalty, and companionship.
-
C.
Forward
Forward is the state motto of Wisconsin, expressing its emphasis on progress and continual improvement.
-
D.
Pursuivant
A Pursuivant is a junior officer of arms in heraldic authorities such as the College of Arms, assisting in matters of coats of arms, genealogy, and ceremonial protocol.
-
E.
Again
"Again" is an R&B ballad by American singer Faith Evans that reflects on her past struggles and personal growth.
- 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_69a8870eea088190a38781990812a9bc |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb37b4a38819099f98be92be91ade |
completed | March 7, 2026, 5:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adfbca5a7081908f3fa8eaa8f5aa3d |
completed | March 8, 2026, 10:44 p.m. |
Created at: March 4, 2026, 7:36 p.m.