Triple
T7263221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rory Culkin |
E159705
|
entity |
| Predicate | actedIn |
P1668
|
FINISHED |
| Object | Mean Creek |
E652765
|
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: Mean Creek | Statement: [Rory Culkin, actedIn, Mean Creek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mean Creek Context triple: [Rory Culkin, actedIn, Mean Creek]
-
A.
Mean Creek
chosen
Mean Creek is a 2004 independent coming-of-age drama film about a group of teenagers whose plan to prank a bully on a river trip spirals into a tragic moral crisis.
-
B.
Warm Creek
Warm Creek is a watercourse in Southern California that flows through the San Bernardino Valley.
-
C.
Dead River
The Dead River is a major river in western Maine known for its remote wilderness setting and popular whitewater rafting opportunities.
-
D.
Cape Fear
Cape Fear is a 1962 psychological thriller film in which Gregory Peck plays a lawyer terrorized by a vengeful ex-convict.
-
E.
Cape Fear
Cape Fear is a prominent headland on the coast of North Carolina, known for its treacherous shoals, maritime history, and role as a key landmark for Atlantic navigation.
- 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_69c68838f9948190875fd60b2351230c |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eac9fab88190881ab9e1cd94cdc1 |
completed | March 27, 2026, 8:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7db175b188190beb5ba5ebb662c9b |
completed | March 28, 2026, 1:43 p.m. |
Created at: March 27, 2026, 2:57 p.m.