Triple
T16481694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Snowmen |
E400333
|
entity |
| Predicate | directedBy |
P7373
|
FINISHED |
| Object | Saul Metzstein |
E1335485
|
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: Saul Metzstein | Statement: [The Snowmen, directedBy, Saul Metzstein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saul Metzstein Context triple: [The Snowmen, directedBy, Saul Metzstein]
-
A.
Saul Metzstein
chosen
Saul Metzstein is a Scottish film and television director known for his work on series such as Doctor Who.
-
B.
Philip Metzger
Philip Metzger is a planetary scientist and former NASA physicist known for his research on lunar and asteroid regolith, in-situ resource utilization, and space industrialization.
-
C.
Alan Metzger
Alan Metzger is an American film and television director known for his work on crime and mystery projects, including the TV movie "The China Lake Murders."
-
D.
Eric Tannenbaum
Eric Tannenbaum is a television producer best known for his work on popular American sitcoms, including serving as an executive producer on "Two and a Half Men."
-
E.
Uriel Weinreich
Uriel Weinreich was a prominent linguist known for his pioneering work in Yiddish studies, language contact, and sociolinguistics.
- 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_69d883813098819084f5409539723b59 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e02b2c881909576a23bfbd3123c |
completed | April 18, 2026, 7:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a071bc0308081908f2b98b0dec96ab6 |
completed | May 15, 2026, 1:12 p.m. |
Created at: April 10, 2026, 5:13 a.m.