Triple
T36207610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abu Zayd al-Saruji |
E1047441
|
entity |
| Predicate | hasCompanionInNarrative |
P30915
|
FINISHED |
| Object | al-Harith ibn Hammam |
E2162025
|
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: al-Harith ibn Hammam | Statement: [Abu Zayd al-Saruji, hasCompanionInNarrative, al-Harith ibn Hammam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCompanionInNarrative Context triple: [Abu Zayd al-Saruji, hasCompanionInNarrative, al-Harith ibn Hammam]
-
A.
hasCompanionInText
Indicates that one entity is accompanied by or associated with another entity within the same textual context or passage.
-
B.
hasPartInNarrative
Indicates that one entity plays a role or participates as a component within the storyline or structure of another narrative entity.
-
C.
hasCompanionCase
Indicates that an entity is associated with another related case that accompanies or parallels it.
-
D.
hasAllyInStory
chosen
Indicates that one entity is portrayed as an ally or supportive partner of another entity within the context of a specific story or narrative.
-
E.
hasSiblingInStory
Indicates that one character in a narrative has at least one sibling who also appears within the same story.
- F. None of above.
Provenance (4 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_69f76e4214748190a76c986d2a1838c2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a396dfc565c8190afa3decee103f5e2 |
completed | June 22, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:09 p.m.