Triple
T16877021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starlight Express |
E421324
|
entity |
| Predicate | centralCharacter |
P9202
|
FINISHED |
| Object | Electra |
E518870
|
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: Electra | Statement: [Starlight Express, centralCharacter, Electra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Electra Context triple: [Starlight Express, centralCharacter, Electra]
-
A.
Electra
Electra is a figure in Greek mythology, traditionally known as one of the Pleiades and a daughter of the Titan Atlas.
-
B.
Electra
chosen
Electra is a figure from Greek mythology, best known as the daughter of Agamemnon and Clytemnestra who helps avenge her father's murder.
-
C.
Electra (Oceanid)
Electra is an Oceanid nymph from Greek mythology, one of the many water-associated daughters of the Titans Oceanus and Tethys.
-
D.
Iphigene
Iphigene Ochs Sulzberger was an American newspaper heiress, civic leader, and influential figure in the family that owned and published The New York Times.
-
E.
Elektra
Elektra is a 2005 superhero film based on the Marvel Comics character, serving as a spin-off from the 2003 movie Daredevil.
- 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_69d889d470fc8190b4aec199636c0c56 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3b7f704a081909921d00b3c470472 |
completed | April 18, 2026, 4:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c2b4abd08190841c5bb0b0eaa177 |
completed | May 10, 2026, 5:39 p.m. |
Created at: April 10, 2026, 5:29 a.m.