Triple
T20901192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Death of Superman (2018 film) |
E514669
|
entity |
| Predicate | featuresLocation |
P7690
|
FINISHED |
| Object | Metropolis |
—
|
NE NERFINISHED |
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: Metropolis | Statement: [The Death of Superman (2018 film), featuresLocation, Metropolis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Metropolis Context triple: [The Death of Superman (2018 film), featuresLocation, Metropolis]
-
A.
Metropolis
Metropolis is a major Ethereum protocol upgrade that introduced significant improvements to scalability, security, and usability of the blockchain.
-
B.
Metropolis
Metropolis is a family of modern, high-capacity metro trains developed by Alstom for urban rapid transit systems worldwide.
-
C.
Metropolis
Metropolis is a science fiction television series inspired by Fritz Lang’s classic 1927 film, exploring a futuristic city divided by class and technological power.
-
D.
Metropolis
Metropolis is a historical crime novel by Philip Kerr featuring detective Bernie Gunther in a pre-World War II Berlin setting.
-
E.
Metropolis
chosen
Metropolis is a DC Comics–themed area in various Six Flags parks, styled as Superman’s iconic city with related rides and attractions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4f8a1108190bce3d31331290ced |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6e8fc5d488190b62f51c35e768d38 |
completed | April 21, 2026, 3:03 a.m. |
Created at: April 16, 2026, 12:47 p.m.