Triple
T1406554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Ozma |
E31704
|
entity |
| Predicate | enemy |
P4567
|
FINISHED |
| Object |
Mombi
Mombi is a wicked witch from L. Frank Baum’s Oz series, best known for usurping and enchanting Princess Ozma to conceal her true identity.
|
E161151
|
NE FINISHED |
How this triple was built (4 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: Mombi | Statement: [Princess Ozma, enemy, Mombi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mombi Context triple: [Princess Ozma, enemy, Mombi]
-
A.
Hamutal
Hamutal was a queen of Judah, known as the mother of the last king of Judah, Zedekiah, during the final years before the Babylonian exile.
-
B.
Rakai Pikatan
Rakai Pikatan was a 9th-century Javanese king of the Medang (Mataram) Kingdom, known for consolidating royal power in Central Java and patronizing major Hindu temple construction.
-
C.
Dora Riparia
Dora Riparia is a river in northwestern Italy that flows through the city of Turin before joining the Po River.
-
D.
Miki
Miki is a city in Japan located within Hyogo Prefecture, known for its traditional hardware industry and historical sites.
-
E.
Dragon Lady
Dragon Lady is the nickname of the Lockheed U-2, a high-altitude American reconnaissance aircraft used extensively for intelligence gathering during the Cold War and beyond.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mombi Triple: [Princess Ozma, enemy, Mombi]
Generated description
Mombi is a wicked witch from L. Frank Baum’s Oz series, best known for usurping and enchanting Princess Ozma to conceal her true identity.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mombi Target entity description: Mombi is a wicked witch from L. Frank Baum’s Oz series, best known for usurping and enchanting Princess Ozma to conceal her true identity.
-
A.
Hamutal
Hamutal was a queen of Judah, known as the mother of the last king of Judah, Zedekiah, during the final years before the Babylonian exile.
-
B.
Rakai Pikatan
Rakai Pikatan was a 9th-century Javanese king of the Medang (Mataram) Kingdom, known for consolidating royal power in Central Java and patronizing major Hindu temple construction.
-
C.
Dora Riparia
Dora Riparia is a river in northwestern Italy that flows through the city of Turin before joining the Po River.
-
D.
Miki
Miki is a city in Japan located within Hyogo Prefecture, known for its traditional hardware industry and historical sites.
-
E.
Dragon Lady
Dragon Lady is the nickname of the Lockheed U-2, a high-altitude American reconnaissance aircraft used extensively for intelligence gathering during the Cold War and beyond.
- F. None of above. chosen
Provenance (5 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_69a49918e1f88190ba610f9dc8114578 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c3be10348190ade8a73780d2c008 |
completed | March 1, 2026, 10:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ace5770ea08190ac91b47a4ed5bf35 |
completed | March 8, 2026, 2:56 a.m. |
| NEDg | Description generation | batch_69ace62a94e88190883d25cdb748e8c1 |
completed | March 8, 2026, 2:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ace68ab3788190bc3b55dd9a0fe267 |
completed | March 8, 2026, 3:01 a.m. |
Created at: March 1, 2026, 7:59 p.m.