Triple
T19981237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chiron |
E493818
|
entity |
| Predicate | loyalTo |
P1201
|
FINISHED |
| Object | Tamora |
—
|
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: Tamora | Statement: [Chiron, loyalTo, Tamora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tamora Context triple: [Chiron, loyalTo, Tamora]
-
A.
Tamora
chosen
Tamora is the vengeful Queen of the Goths and a central antagonist in William Shakespeare’s tragedy "Titus Andronicus."
-
B.
Morgawse
Morgawse is a prominent figure in Arthurian legend, typically depicted as King Arthur’s half-sister and the mother of several of the Knights of the Round Table, including Gawain.
-
C.
Vala Mal Doran
Vala Mal Doran is a roguish, quick-witted former thief and con artist who becomes an ally and later a member of the SG-1 team in the science fiction television series Stargate SG-1.
-
D.
Blood-Queen Lana'thel
Blood-Queen Lana'thel is a powerful vampiric San'layn queen and raid boss in World of Warcraft, encountered in the Icecrown Citadel raid.
-
E.
Damara
The Damara are an indigenous ethnic group of Namibia known for their distinct language, rich oral traditions, and historical presence in the country’s northwestern regions.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65d12d968819081e315ec4585cd9f |
completed | April 20, 2026, 5:06 p.m. |
Created at: April 11, 2026, 3:28 p.m.