Triple
T20931316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siyavash |
E515476
|
entity |
| Predicate | marries |
P23691
|
FINISHED |
| Object |
Farangis
Farangis is a noblewoman in the Persian epic Shahnameh, best known as the wife of the tragic hero Siyavash and the mother of the legendary prince Kay Khosrow.
|
E1458059
|
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: Farangis | Statement: [Siyavash, marries, Farangis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Farangis Context triple: [Siyavash, marries, Farangis]
-
A.
Gurandukht
Gurandukht was a medieval Georgian noblewoman and queen consort, known primarily as the wife of King David IV "the Builder" of Georgia.
-
B.
Gurandukht
Gurandukht was a medieval Cuman princess known from Georgian and regional Caucasian historical sources, often mentioned in the context of dynastic and political alliances.
-
C.
Roxanna
Roxanna is a feminine given name of Persian origin, commonly interpreted to mean "dawn" or "bright."
-
D.
Fedalma
Fedalma is a notable painting by American artist George Fuller, recognized for its evocative, romantic style and atmospheric portrayal of its female subject.
-
E.
Farahnaz
Farahnaz is a Persian female given name, notably borne by Farahnaz Pahlavi, the eldest daughter of the former Shah of Iran, Mohammad Reza Pahlavi.
- 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: Farangis Triple: [Siyavash, marries, Farangis]
Generated description
Farangis is a noblewoman in the Persian epic Shahnameh, best known as the wife of the tragic hero Siyavash and the mother of the legendary prince Kay Khosrow.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Farangis Target entity description: Farangis is a noblewoman in the Persian epic Shahnameh, best known as the wife of the tragic hero Siyavash and the mother of the legendary prince Kay Khosrow.
-
A.
Gurandukht
Gurandukht was a medieval Georgian noblewoman and queen consort, known primarily as the wife of King David IV "the Builder" of Georgia.
-
B.
Gurandukht
Gurandukht was a medieval Cuman princess known from Georgian and regional Caucasian historical sources, often mentioned in the context of dynastic and political alliances.
-
C.
Roxanna
Roxanna is a feminine given name of Persian origin, commonly interpreted to mean "dawn" or "bright."
-
D.
Fedalma
Fedalma is a notable painting by American artist George Fuller, recognized for its evocative, romantic style and atmospheric portrayal of its female subject.
-
E.
Farahnaz
Farahnaz is a Persian female given name, notably borne by Farahnaz Pahlavi, the eldest daughter of the former Shah of Iran, Mohammad Reza Pahlavi.
- 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_69e0b4fb431c8190b9d40e6a72f0cc87 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f6557e4881909ce932c3f538304a |
completed | April 21, 2026, 4 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a091fd064248190ae7ae1c980b68b8c |
completed | May 17, 2026, 1:54 a.m. |
| NEDg | Description generation | batch_6a0920c37ec48190a043097a24151022 |
completed | May 17, 2026, 1:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09219be3c48190a610062e59e05876 |
completed | May 17, 2026, 2:02 a.m. |
Created at: April 16, 2026, 12:49 p.m.