Triple
T16623636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LexCorp |
E403891
|
entity |
| Predicate | headquartersLocation |
P62
|
FINISHED |
| Object | Metropolis |
E199719
|
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: Metropolis | Statement: [LexCorp, headquartersLocation, Metropolis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Metropolis Context triple: [LexCorp, headquartersLocation, 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 major urban area of London that historically fell under the jurisdiction of Peel’s Act, which established the modern professional police force.
-
E.
Metropolis
chosen
Metropolis is a fictional, futuristic American city in the DC Comics universe, best known as Superman’s primary home and the backdrop for many of his stories.
- 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_69d883897eb481909eaaa088ba9918d9 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3754f4f508190a5b4b8511623fcd4 |
completed | April 18, 2026, 12:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a007db4a9288190aea7db58bb379404 |
completed | May 10, 2026, 12:44 p.m. |
Created at: April 10, 2026, 5:17 a.m.