Triple
T8266130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mursili II |
E193305
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Henti |
E722158
|
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: Henti | Statement: [Mursili II, mother, Henti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henti Context triple: [Mursili II, mother, Henti]
-
A.
Henti
chosen
Henti was a queen of the Hittite Empire, known primarily as the wife of the powerful 14th-century BCE king Suppiluliuma I.
-
B.
Halt
Halt is the surname of Karl Ritter von Halt, a notable German sports official and International Olympic Committee member in the early to mid-20th century.
-
C.
Ponto de Parada
Ponto de Parada is a neighborhood in the city of Recife, Brazil, known primarily as a residential area within the metropolitan region.
-
D.
Shikasta
Shikasta is a 1979 science fiction novel by Doris Lessing that inaugurates her Canopus in Argos series, blending cosmic history with political and spiritual allegory.
-
E.
Toinette
Toinette is the sharp-witted, outspoken maid in Molière’s comedy "Le Malade imaginaire," known for her clever schemes and satirical commentary on her hypochondriac master.
- 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_69ca82e081d48190986beaa51f498ab9 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb794e6880819084dff5df42332835 |
completed | March 31, 2026, 7:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd6827e44c81909be6e426ab9226c7 |
completed | April 1, 2026, 6:47 p.m. |
Created at: March 30, 2026, 5:50 p.m.