Triple
T20931427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | White Div |
E515479
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object |
Div-e Sefid
Div-e Sefid is a formidable white demon from Persian mythology, best known as a major antagonist in the epic poem Shahnameh.
|
E1458062
|
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: Div-e Sefid | Statement: [White Div, alsoKnownAs, Div-e Sefid]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Div-e Sefid Context triple: [White Div, alsoKnownAs, Div-e Sefid]
-
A.
Mezallat
Mezallat is a passenger station on Cairo Metro’s Line 2 serving commuters in the Greater Cairo area.
-
B.
Shab-e-Rafta
Shab-e-Rafta is a celebrated Urdu poetry collection by Pakistani poet Majeed Amjad, noted for its introspective, modernist themes and distinctive lyrical style.
-
C.
Mojaddedi
Mojaddedi is an Afghan family name most prominently associated with Sibghatullah Mojaddedi, a key political and religious figure in Afghanistan’s modern history.
-
D.
Ghal'eh Dokhtar
Ghal'eh Dokhtar is an ancient Sasanian-era fortress in Iran, renowned for its strategic hilltop location and early example of Sasanian defensive and palatial architecture.
-
E.
Baghban
Baghban is a 2003 Hindi drama film about aging parents facing neglect from their grown children, starring Amitabh Bachchan and Hema Malini.
- 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: Div-e Sefid Triple: [White Div, alsoKnownAs, Div-e Sefid]
Generated description
Div-e Sefid is a formidable white demon from Persian mythology, best known as a major antagonist in the epic poem Shahnameh.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Div-e Sefid Target entity description: Div-e Sefid is a formidable white demon from Persian mythology, best known as a major antagonist in the epic poem Shahnameh.
-
A.
Mezallat
Mezallat is a passenger station on Cairo Metro’s Line 2 serving commuters in the Greater Cairo area.
-
B.
Shab-e-Rafta
Shab-e-Rafta is a celebrated Urdu poetry collection by Pakistani poet Majeed Amjad, noted for its introspective, modernist themes and distinctive lyrical style.
-
C.
Mojaddedi
Mojaddedi is an Afghan family name most prominently associated with Sibghatullah Mojaddedi, a key political and religious figure in Afghanistan’s modern history.
-
D.
Ghal'eh Dokhtar
Ghal'eh Dokhtar is an ancient Sasanian-era fortress in Iran, renowned for its strategic hilltop location and early example of Sasanian defensive and palatial architecture.
-
E.
Baghban
Baghban is a 2003 Hindi drama film about aging parents facing neglect from their grown children, starring Amitabh Bachchan and Hema Malini.
- 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_69e6f65681b4819083c7ef6b44ba4bdb |
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.