Triple
T14308958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Missandei |
E354771
|
entity |
| Predicate | culture |
P1114
|
FINISHED |
| Object | Naathi |
E1092373
|
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: Naathi | Statement: [Missandei, culture, Naathi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Naathi Context triple: [Missandei, culture, Naathi]
-
A.
Naath
chosen
Naath is a peaceful, isolated island in the world of "Game of Thrones" known as the homeland of the translator Missandei and its gentle, pacifist inhabitants.
-
B.
Naath
Naath is the self-designation of the Nuer people, a Nilotic ethnic group primarily inhabiting regions of South Sudan and western Ethiopia.
-
C.
Tharkha
Tharkha is a traditional musical form or instrument associated with the cultural heritage and folk music of the Bodo people of Northeast India.
-
D.
Shaath
Shaath is an Arabic family name notably borne by Palestinian politician and diplomat Nabil Shaath.
-
E.
Thari
Thari is a regional dialect of the Sindhi language spoken primarily in the Thar Desert region of Pakistan and India.
- 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_69d8278ed42c8190b9f882dcce611347 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de85b26da48190a96e2f60ace51335 |
completed | April 14, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5504dc6c8190a4d8a5985632901d |
completed | May 8, 2026, 3:14 a.m. |
Created at: April 10, 2026, 1:12 a.m.