Triple
T17311454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hettie MacDonald |
E420306
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Blink |
E1014063
|
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: Blink | Statement: [Hettie MacDonald, directed, Blink]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blink Context triple: [Hettie MacDonald, directed, Blink]
-
A.
Blink
Blink is an open-source web browser engine developed primarily by Google and used in several major browsers to render web pages.
-
B.
Blink
Blink is a bestselling nonfiction book by Malcolm Gladwell that explores the power and pitfalls of rapid, intuitive decision-making.
-
C.
Blink
"Blink" is a widely acclaimed, time-bending episode of the British science fiction series Doctor Who, renowned for introducing the terrifying Weeping Angels and its minimal use of the Doctor.
-
D.
Blink
Blink is Tracer’s signature short-range teleportation move in Overwatch, allowing her to rapidly reposition in quick bursts.
-
E.
Blink
chosen
"Blink" is a 1994 neo-noir thriller film about a partially restored blind woman who becomes entangled in a murder investigation after believing she has witnessed a crime.
- 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439993bac8190a72f6af529bd7cce |
completed | April 19, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a018c4603f88190a713bf8260329ac3 |
completed | May 11, 2026, 7:59 a.m. |
Created at: April 10, 2026, 5:43 a.m.