Triple
T12912916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terra |
E308903
|
entity |
| Predicate | alias |
P39
|
FINISHED |
| Object | Terra |
unclear NED1
|
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: Terra | Statement: [Terra, alias, Terra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terra Context triple: [Terra, alias, Terra]
-
A.
Terra
Terra is a sustainability-themed character created as one of the official mascots for Expo 2020 Dubai, symbolizing environmental awareness and ecological responsibility.
-
B.
Terra
Terra is a character from the film "I, Frankenstein," depicted as a central figure within its dark, supernatural world of gargoyles and demons.
-
C.
Terra
Terra is a fictional character best known as the troubled, earth-controlling teen superheroine from DC Comics' Teen Titans franchise.
-
D.
Erda
Erda is the earth goddess and prophetic figure in Richard Wagner’s Ring Cycle, renowned for her wisdom and warnings to the gods.
-
E.
La Terre
La Terre is a naturalist novel by Émile Zola that portrays the brutal lives, struggles, and moral decay of French peasants in the 19th century countryside.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d7bdf92b588190acdf2a2291ac4590 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9719f96248190b746f9d4a468560c |
completed | April 10, 2026, 9:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6cbbccbd08190869d8de09797bc6a |
completed | May 3, 2026, 4:14 a.m. |
Created at: April 9, 2026, 5:41 p.m.